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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in data

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

    Characters in math expressions or code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions or code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getDoctrine
    -0.53
    ]='\
    -0.48
     Cobb
    -0.48
    <?=$
    -0.48
    QString
    -0.47
     emphas
    -0.47
    Dış
    -0.46
    を取
    -0.44
     كمان
    -0.44
    InteropServices
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.79
    ']));
    0.68
    ]));
    0.66
    Personensuche
    0.65
    extAlignment
    0.64
     تانيه
    0.60
     مرئيه
    0.58
     skippy
    0.58
    ']],
    0.57
    crollView
    0.57
    Act Density 0.282%

    No Known Activations