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

    Neuronpedia

    INDEX
    Explanations

    а

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LAY
    -0.07
     باب
    -0.07
    locks
    -0.07
    ウィ
    -0.07
    enses
    -0.06
    ресс
    -0.06
     Bearing
    -0.06
    isty
    -0.06
    ;")↵
    -0.06
     Ле
    -0.06
    POSITIVE LOGITS
    SPA
    0.06
    Comple
    0.06
    CGFloat
    0.06
     Moving
    0.06
     а
    0.06
     Aeros
    0.06
    Visited
    0.06
    &p
    0.06
     catering
    0.06
     FORE
    0.06
    Act Density 0.004%

    No Known Activations