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

    Neuronpedia

    INDEX
    Explanations

    sports disqualifications/scandals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emergency
    -0.07
    .original
    -0.07
    _summary
    -0.06
    voje
    -0.06
    .firstChild
    -0.06
    IO
    -0.06
    Dou
    -0.06
     Explain
    -0.06
     Married
    -0.06
    "<
    -0.06
    POSITIVE LOGITS
     decorators
    0.06
    ApiModelProperty
    0.06
     centroid
    0.06
     �
    0.06
    人は
    0.06
    明白
    0.06
     dělat
    0.06
    OfWork
    0.06
     перевір
    0.06
    TOR
    0.06
    Act Density 0.116%

    No Known Activations