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

    Neuronpedia

    INDEX
    Explanations

    references to comprehensiveness and the need to address all aspects of an issue

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

    every, all, both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    none
    -0.39
    KP
    -0.33
    table
    -0.33
    pic
    -0.32
     none
    -0.32
    大
    -0.32
    도
    -0.32
    None
    -0.31
    pro
    -0.30
    kra
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.77
     autorytatywna
    0.75
    تقاوى
    0.71
     avoient
    0.69
    IntoConstraints
    0.69
    Personendaten
    0.69
     Anſ
    0.66
    errHandler
    0.65
    httphttps
    0.63
     transfieras
    0.62
    Act Density 0.064%

    No Known Activations