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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ться
    0.96
    вается
    0.90
    оны
    0.89
     in
    0.88
     बोस
    0.88
    inationals
    0.87
     to
    0.85
     subsidies
    0.83
    న్నో
    0.82
    оне
    0.82
    POSITIVE LOGITS
     estudi
    1.09
    `
    1.06
    didn
    1.02
    <blockquote>
    0.98
    1
    0.98
     immediatamente
    0.97
    2
    0.95
    ie
    0.95
    '
    0.95
    ²
    0.94
    Act Density 0.008%

    No Known Activations