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

    Neuronpedia

    INDEX
    Explanations

    numerical references and timestamps

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.82
    AndEndTag
    -0.77
     snippetHide
    -0.77
    /*
    -0.75
    AddTagHelper
    -0.74
     geſch
    -0.73
    principalTable
    -0.72
    IntoConstraints
    -0.70
     вікісторінку
    -0.67
    OUTUBE
    -0.67
    POSITIVE LOGITS
    カル
    0.29
     tör
    0.27
     '',
    0.24
    ・・・
    0.23
    wahl
    0.23
     crimen
    0.23
    ...
    0.23
     nở
    0.22
    Leggi
    0.22
    :
    0.22
    Act Density 0.003%

    No Known Activations