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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fight
    -0.07
     handguns
    -0.07
     لإ
    -0.06
     یعنی
    -0.06
     disclosed
    -0.06
    _identifier
    -0.06
    टन
    -0.06
    .system
    -0.06
     broaden
    -0.06
    -theme
    -0.06
    POSITIVE LOGITS
    Pay
    0.06
     charity
    0.06
     κύ
    0.06
     ERC
    0.06
    англ
    0.06
    pay
    0.06
    Criterion
    0.06
    ेग
    0.06
    CAT
    0.06
    orama
    0.06
    Act Density 0.000%

    No Known Activations