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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    泜
    -0.07
    ע
    -0.07
    ạc
    -0.06
     Dek
    -0.06
    .Constant
    -0.06
     תע
    -0.06
    pływ
    -0.06
    ۉ
    -0.06
     developers
    -0.06
    brush
    -0.06
    POSITIVE LOGITS
    净值
    0.07
    bery
    0.07
    سد
    0.07
    嚇
    0.07
    支部
    0.07
     optimization
    0.07
    唬
    0.07
    漂亮的
    0.07
     ethics
    0.07
     certifications
    0.06
    Act Density 0.021%

    No Known Activations