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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GroupName
    -0.07
     September
    -0.06
    血
    -0.06
    Њ
    -0.06
     Democrat
    -0.06
    Rub
    -0.06
    」
    -0.06
     Vin
    -0.06
    ซ
    -0.06
     تغییر
    -0.06
    POSITIVE LOGITS
    enting
    0.07
     Receiver
    0.07
     tolik
    0.07
     oluşan
    0.07
    lâm
    0.06
    atism
    0.06
     uncert
    0.06
    (';
    0.06
     amazingly
    0.06
     Swagger
    0.06
    Act Density 0.003%

    No Known Activations