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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    地址
    -0.08
     ramp
    -0.07
    �
    -0.07
     rod
    -0.07
     scrapy
    -0.07
     gql
    -0.07
    .sol
    -0.07
    _diag
    -0.07
     Zak
    -0.07
     ============================================================================↵
    -0.07
    POSITIVE LOGITS
    텁
    0.07
     homemade
    0.06
     HTTPS
    0.06
    𝓱
    0.06
     dotyczące
    0.06
     şey
    0.06
     Ш
    0.06
    Activation
    0.06
    ется
    0.06
    .InnerException
    0.06
    Act Density 0.010%

    No Known Activations