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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    واز
    -0.08
     genuine
    -0.07
     marry
    -0.07
     answers
    -0.07
     eu
    -0.07
     races
    -0.07
    _geometry
    -0.07
     geometry
    -0.07
    _buttons
    -0.06
    ==============
    -0.06
    POSITIVE LOGITS
     audi
    0.07
     ра�
    0.06
     SX
    0.06
    ‚ط
    0.06
    abez
    0.06
    ブロ
    0.06
    .Pin
    0.06
     зак
    0.06
    .Lerp
    0.06
     Lisp
    0.05
    Act Density 0.137%

    No Known Activations