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

    Neuronpedia

    INDEX
    Explanations

    -d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בחדר
    -0.08
     Caucasian
    -0.08
    [mask
    -0.07
     faire
    -0.07
    ��
    -0.07
     meget
    -0.07
     Reminder
    -0.07
    อาการ
    -0.07
     desarrollo
    -0.07
    .PackageManager
    -0.07
    POSITIVE LOGITS
     Until
    0.07
     Watts
    0.07
     twenties
    0.07
    View
    0.07
     hooks
    0.06
     prefs
    0.06
    磷
    0.06
    待
    0.06
    chedules
    0.06
    PECT
    0.06
    Act Density 0.002%

    No Known Activations