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
    spam
    -0.07
    .Fail
    -0.07
    □□
    -0.07
    大学
    -0.06
    "*
    -0.06
    _POP
    -0.06
     жар
    -0.06
     Accounting
    -0.06
    _database
    -0.06
    ('?
    -0.06
    POSITIVE LOGITS
     sodium
    0.06
     застосування
    0.06
    .compare
    0.06
    Genesis
    0.06
     celkem
    0.06
    enheim
    0.06
     Reported
    0.06
    ometer
    0.06
    ificação
    0.06
     Prize
    0.06
    Act Density 0.020%

    No Known Activations