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

    Neuronpedia

    INDEX
    Explanations

    linux

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     card
    -0.07
     objectives
    -0.07
     ↓
    -0.07
    copy
    -0.07
     соответствии
    -0.07
     OrderedDict
    -0.06
     brunette
    -0.06
     Filtering
    -0.06
    _patient
    -0.06
     subtype
    -0.06
    POSITIVE LOGITS
    $q
    0.07
     finde
    0.07
     madness
    0.07
    Minnesota
    0.07
     |_
    0.06
     قائمة
    0.06
     نگاه
    0.06
    aze
    0.06
     assorted
    0.06
    mn
    0.06
    Act Density 0.002%

    No Known Activations