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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rx
    -0.07
    dac
    -0.07
     seiz
    -0.07
    цо
    -0.07
    .lp
    -0.07
    racial
    -0.07
    овано
    -0.06
    |wx
    -0.06
     öğret
    -0.06
     bez
    -0.06
    POSITIVE LOGITS
    -approved
    0.06
    699
    0.06
     FName
    0.06
    _MOVE
    0.06
    _INSTANCE
    0.06
     часу
    0.06
    Difference
    0.06
    iron
    0.06
    錯
    0.06
    (button
    0.06
    Act Density 0.000%

    No Known Activations