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

    Neuronpedia

    INDEX
    Explanations

    Code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ishop
    -0.07
    搜索
    -0.06
    iral
    -0.06
     sunday
    -0.06
    ãy
    -0.06
    dance
    -0.06
    burn
    -0.06
    елич
    -0.06
    １
    -0.06
    .misc
    -0.06
    POSITIVE LOGITS
    operator
    0.08
    ausible
    0.07
    ávací
    0.06
     (%)
    0.06
     ruthless
    0.06
     RATE
    0.06
     pem
    0.06
    didn
    0.06
    尺
    0.06
     Governance
    0.06
    Act Density 0.036%

    No Known Activations