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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uy
    -0.06
     �
    -0.06
     取
    -0.06
    ổ
    -0.06
     urgency
    -0.06
    عود
    -0.06
    確認
    -0.06
     manuals
    -0.06
    ulla
    -0.06
    _fatal
    -0.06
    POSITIVE LOGITS
    prise
    0.07
    761
    0.07
    Neill
    0.07
    (question
    0.06
    _VERSION
    0.06
     advertis
    0.06
    tridges
    0.06
     (__
    0.06
    /api
    0.06
     Agriculture
    0.06
    Act Density 0.000%

    No Known Activations