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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics and performance metrics

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

    before "for"

    np_acts-logits-general · gemini-2.0-flash

    finding words followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     policing
    -0.69
     فريبيس
    -0.68
    ValueStyle
    -0.62
     '\\;'
    -0.61
     Policing
    -0.58
    vallis
    -0.58
     Nye
    -0.56
    webElementXpaths
    -0.54
     Trench
    -0.54
    fony
    -0.54
    POSITIVE LOGITS
    mobileqq
    0.56
    RTLR
    0.53
    Destin
    0.51
     Illumin
    0.49
     thiệu
    0.48
    ELIA
    0.44
    kriegs
    0.44
    Œuvres
    0.44
    瞄
    0.44
     απε
    0.44
    Act Density 0.182%

    No Known Activations