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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     achieves
    -0.07
    这么久
    -0.07
    变为
    -0.07
    _AA
    -0.07
    喜欢
    -0.07
    ($.
    -0.07
    都可以
    -0.06
    (newValue
    -0.06
     sings
    -0.06
    就可以了
    -0.06
    POSITIVE LOGITS
     bigot
    0.07
    pipe
    0.07
     autos
    0.07
    -serif
    0.07
     apartheid
    0.06
    cery
    0.06
     Hindus
    0.06
     heir
    0.06
    ryan
    0.06
     hü
    0.06
    Act Density 0.003%

    No Known Activations