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

    Neuronpedia

    INDEX
    Explanations

    personality types

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shear
    -0.07
    枢
    -0.07
    䴕
    -0.07
    痔
    -0.07
     transparency
    -0.07
     heading
    -0.06
    𝒿
    -0.06
    (mutex
    -0.06
    有一些
    -0.06
    prises
    -0.06
    POSITIVE LOGITS
     Bradley
    0.07
     Goat
    0.07
    不由得
    0.07
     valide
    0.07
     النفس
    0.07
    前列腺
    0.07
    קני
    0.07
    爱奇艺
    0.07
    ORA
    0.07
     Youtube
    0.06
    Act Density 0.017%

    No Known Activations