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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IndexChanged
    -0.06
    659
    -0.06
     differs
    -0.06
     motif
    -0.06
    ’B
    -0.06
     الرسم
    -0.06
    652
    -0.06
    'B
    -0.06
    205
    -0.06
    バー
    -0.06
    POSITIVE LOGITS
     Enumeration
    0.06
     verses
    0.06
     日本
    0.06
     urlpatterns
    0.06
    numero
    0.06
    _fields
    0.06
    ized
    0.06
    치는
    0.06
    uff
    0.06
     deserved
    0.06
    Act Density 0.015%

    No Known Activations