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

    Neuronpedia

    INDEX
    Explanations

    code snippets, especially Python code, including keywords, operators, and print statements.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.54
     App
    -0.51
    iconductor
    -0.48
    må
    -0.47
    bourhood
    -0.46
     app
    -0.46
     Bar
    -0.45
    ircut
    -0.45
    OWSKI
    -0.45
    carter
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.67
    اریخ
    0.67
     blest
    0.65
    出版年
    0.64
     Pues
    0.62
    //
    0.62
    ThroughAttribute
    0.61
    UnusedPrivate
    0.58
     heretics
    0.58
     للمعارف
    0.57
    Act Density 0.946%

    No Known Activations