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

    Neuronpedia

    INDEX
    Explanations

    time durations and measurements

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

    Durations of time (weeks, months)

    np_acts-logits-general · gemini-2.0-flash

    duration in months or weeks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conservative
    -0.39
     southwestern
    -0.35
    Conservative
    -0.33
    CONSTANT
    -0.33
    RequestHandler
    -0.32
     Cow
    -0.32
    rull
    -0.32
     First
    -0.31
     barb
    -0.31
     NU
    -0.31
    POSITIVE LOGITS
    OptionsMenu
    0.61
     invokingState
    0.60
    AddTagHelper
    0.59
    GraphicsUnit
    0.56
    ⓧ
    0.56
     desertcart
    0.54
     autorytatywna
    0.52
     ब्रेकडाउन
    0.51
    adaptiveStyles
    0.50
    UnusedPrivate
    0.50
    Act Density 0.442%

    No Known Activations