Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantitative measures and statistical values in scientific data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Values with "±" (plus/minus)

    np_acts-logits-general · gemini-2.0-flash

    ±0.2%, ±0.4%, ±6.0%, ±0.16%, ±1.31%, ±0,07, ±3,56, ±18,04, ±8, ±10.0%, ±13, ±0.87, ±2.8, ±14.9%, ±2.6, ±7.1%

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ništvo
    -0.56
    principalTable
    -0.54
     ref
    -0.47
    ThemeOverlay
    -0.46
     ý
    -0.46
    цездатний
    -0.46
    RTGC
    -0.45
    يكب
    -0.45
    ref
    -0.44
    #
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.01
     myſelf
    0.81
    ImageContext
    0.78
    UIControlState
    0.75
    ]='\
    0.73
     itſelf
    0.72
    InSection
    0.72
     imageNamed
    0.70
     NSCoder
    0.70
    leſs
    0.68
    Act Density 0.465%

    No Known Activations