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

    Neuronpedia

    INDEX
    Explanations

    mentions of variables within a programming context

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

    scope access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    postsleuth
    -0.41
     незавершена
    -0.40
    /**
    -0.37
    Bibliograf
    -0.37
    oa̍t
    -0.36
    /*++
    -0.34
     Италијани
    -0.33
    transQ
    -0.33
    keyColumn
    -0.32
     pinulongan
    -0.32
    POSITIVE LOGITS
    scope
    2.72
     scope
    2.14
    Scope
    2.06
     Scope
    1.94
    SCOPE
    1.85
     SCOPE
    1.70
     scopes
    1.67
    scopes
    1.45
    cope
    1.45
    Scopes
    1.33
    Act Density 0.003%

    No Known Activations