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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .place
    -0.07
    (delay
    -0.06
     레이
    -0.06
    ंय
    -0.06
    чу
    -0.06
     Snapshot
    -0.06
    �
    -0.06
    Limit
    -0.06
     Checkbox
    -0.06
    minated
    -0.06
    POSITIVE LOGITS
     LIABILITY
    0.06
    ۱۹۵
    0.06
     cookbook
    0.06
    MENT
    0.06
    _RSA
    0.06
    یت
    0.06
    /blue
    0.06
     giác
    0.06
     наказ
    0.06
     ("-
    0.06
    Act Density 0.021%

    No Known Activations