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

    Neuronpedia

    INDEX
    Explanations

    mutagenesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PhD
    -0.07
     interviews
    -0.07
    queries
    -0.07
    лон
    -0.07
    BODY
    -0.07
    럭
    -0.07
    Near
    -0.07
    Q
    -0.06
    Certain
    -0.06
    -question
    -0.06
    POSITIVE LOGITS
    .mas
    0.06
     defStyleAttr
    0.06
     abrasive
    0.06
    _PWM
    0.06
     tg
    0.06
     anomalies
    0.06
    /ms
    0.06
     kari
    0.05
    breadcrumbs
    0.05
     nä
    0.05
    Act Density 0.047%

    No Known Activations