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

    Neuronpedia

    INDEX
    Explanations

    ethics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卢
    -0.07
    .ViewModel
    -0.07
     Reb
    -0.07
    漏
    -0.07
    ازند
    -0.07
    .L
    -0.06
     };
    -0.06
    .Download
    -0.06
    มาร
    -0.06
    (rv
    -0.06
    POSITIVE LOGITS
     ethics
    0.11
     Ethics
    0.10
     Bearings
    0.06
    resas
    0.06
     Airbus
    0.06
    _Enter
    0.06
     aggression
    0.06
     burglary
    0.06
     aerospace
    0.06
    -ever
    0.06
    Act Density 0.004%

    No Known Activations