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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quent
    -0.07
    갓
    -0.06
    -over
    -0.06
     Communities
    -0.06
     Arbitrary
    -0.06
    otor
    -0.06
     standby
    -0.06
     affects
    -0.06
    -ion
    -0.06
    .if
    -0.06
    POSITIVE LOGITS
    ره
    0.07
    نسب
    0.07
    adresse
    0.07
    [np
    0.07
    øre
    0.07
    名声
    0.07
    codes
    0.07
    꺄
    0.06
    мысл
    0.06
    認め
    0.06
    Act Density 0.074%

    No Known Activations