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

    Neuronpedia

    INDEX
    Explanations

    radius

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shared
    -0.07
    for
    -0.06
     конечно
    -0.06
    sel
    -0.06
    .firstName
    -0.06
    син
    -0.06
    貊
    -0.06
    Touchable
    -0.06
    速
    -0.06
    쏩
    -0.06
    POSITIVE LOGITS
    рез
    0.07
     exc
    0.07
    ┏
    0.07
    'ex
    0.07
     shredd
    0.06
    办案
    0.06
     bathrooms
    0.06
    ’ex
    0.06
    をつけ
    0.06
    (AdapterView
    0.06
    Act Density 0.004%

    No Known Activations