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
    .cent
    -0.07
    <LM
    -0.07
    香
    -0.06
    好的
    -0.06
    ूल
    -0.06
     terk
    -0.06
    :${
    -0.06
    少
    -0.06
    ับค
    -0.06
    @index
    -0.06
    POSITIVE LOGITS
     Moines
    0.07
    织
    0.07
     climbed
    0.06
    MatrixXd
    0.06
     stě
    0.06
     ))
    0.06
     user
    0.06
    scopes
    0.06
     arranged
    0.06
     Oakland
    0.06
    Act Density 0.002%

    No Known Activations