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

    Neuronpedia

    INDEX
    Explanations

    headings or section titles in a document

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

    Tokens after heading tags or delimiters

    np_acts-logits-general · gemini-2.0-flash

    section headers or code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.62
    Jeografia
    -0.62
    DockStyle
    -0.60
     Brody
    -0.57
    حياتها
    -0.57
    ніципалі
    -0.54
    IsMutable
    -0.53
     Мексичка
    -0.52
     Gegenteil
    -0.52
    AnchorStyles
    -0.51
    POSITIVE LOGITS
    <h2>
    1.69
    ing
    0.89
    <th>
    0.63
    /*!
    0.62
    /*
    0.60
    /*
    0.59
    </h2>
    0.56
    ING
    0.55
    ##
    0.54
     /*
    0.54
    Act Density 0.055%

    No Known Activations