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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rolls
    -0.07
     assaults
    -0.06
     burglary
    -0.06
    ek
    -0.06
    约
    -0.06
    ่ว
    -0.06
     payout
    -0.06
    unner
    -0.06
    taj
    -0.06
     академ
    -0.06
    POSITIVE LOGITS
    จะต
    0.07
    ltra
    0.07
     psyched
    0.06
    [state
    0.06
     causa
    0.06
    .LogError
    0.06
    .ex
    0.06
     Prest
    0.06
    real
    0.06
    _UTF
    0.06
    Act Density 0.037%

    No Known Activations