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

    Neuronpedia

    INDEX
    Explanations

    Review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵                    ↵
    -0.06
     найти
    -0.06
     saints
    -0.06
     처
    -0.06
     Browns
    -0.06
     سرم
    -0.06
    :^{↵
    -0.06
     Ca
    -0.06
     будинку
    -0.06
    .outer
    -0.06
    POSITIVE LOGITS
    _expr
    0.06
    ốc
    0.06
    0.06
    0.06
     upheld
    0.06
     kept
    0.06
     "]"
    0.06
    (iv
    0.06
     Wanted
    0.06
     معت
    0.06
    Act Density 0.003%

    No Known Activations