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

    Neuronpedia

    INDEX
    Explanations

    encode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    redirectTo
    -0.06
    lil
    -0.06
     skull
    -0.06
     Čech
    -0.06
     dialogs
    -0.06
    .usermodel
    -0.06
    (expr
    -0.06
    scores
    -0.06
    Links
    -0.06
    цями
    -0.06
    POSITIVE LOGITS
     ε�
    0.08
     GENERATED
    0.07
     homemade
    0.07
    _SC
    0.06
     tropical
    0.06
     insist
    0.06
    ？
    0.06
     zda
    0.06
    εια
    0.06
    emade
    0.06
    Act Density 0.017%

    No Known Activations