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

    Neuronpedia

    INDEX
    Explanations

    patch files and code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.83
    N
    0.78
     for
    0.74
    ך
    0.71
     proporcion
    0.71
     surgi
    0.71
     divul
    0.70
    IL
    0.69
    ES
    0.68
     arose
    0.68
    POSITIVE LOGITS
    いろんな
    0.78
    いろいろ
    0.71
     is
    0.71
    v
    0.70
    brane
    0.64
     तब
    0.63
    mar
    0.61
    ске
    0.61
     continents
    0.61
    andelion
    0.61
    Act Density 0.000%

    No Known Activations