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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    履
    -0.06
     liver
    -0.05
    ์แ
    -0.05
    Compound
    -0.05
    バ
    -0.05
     rev
    -0.05
    .email
    -0.05
     VA
    -0.05
    oods
    -0.05
     Guil
    -0.05
    POSITIVE LOGITS
     Mayweather
    0.08
     yürüy
    0.07
     Estr
    0.07
    esar
    0.07
     Native
    0.07
     @"
    0.07
     Gn
    0.06
     stren
    0.06
     GOD
    0.06
    (Photo
    0.06
    Act Density 0.000%

    No Known Activations