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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "$
    -0.06
    ，对
    -0.06
     sát
    -0.06
     Maver
    -0.06
    adding
    -0.06
     Ricky
    -0.06
     默认
    -0.06
    .requestFocus
    -0.06
    �
    -0.06
     رمز
    -0.06
    POSITIVE LOGITS
    няття
    0.07
     získal
    0.06
     Neal
    0.06
     instruments
    0.06
    jom
    0.06
    穴
    0.06
     animations
    0.06
     anytime
    0.06
    ,,,
    0.06
    _music
    0.06
    Act Density 0.037%

    No Known Activations