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

    Neuronpedia

    INDEX
    Explanations

    deal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tears
    -0.07
    ژی
    -0.07
     casos
    -0.07
     prized
    -0.06
     흔
    -0.06
     pois
    -0.06
     film
    -0.06
     puberty
    -0.06
    .getColumnIndex
    -0.06
     nueva
    -0.06
    POSITIVE LOGITS
    hiba
    0.07
    quare
    0.06
     푸
    0.06
    ROI
    0.06
    ub
    0.06
    startdate
    0.06
    /settings
    0.06
     understanding
    0.06
    uda
    0.06
    RO
    0.06
    Act Density 0.020%

    No Known Activations