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
    cript
    -0.08
    prep
    -0.08
    _plain
    -0.08
    -0.08
    ipper
    -0.07
     outsiders
    -0.07
     المشكلة
    -0.07
    -normal
    -0.07
    ynth
    -0.07
    ▄
    -0.07
    POSITIVE LOGITS
     spaced
    0.10
     listar
    0.09
     numbering
    0.08
    รายการ
    0.08
     покол
    0.08
     spacing
    0.08
     hingga
    0.08
     successive
    0.08
     lif
    0.08
     தொட
    0.08
    Act Density 0.043%
    No Known Activations