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

    Neuronpedia

    INDEX
    Explanations

    statement terminator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مسلسل
    -0.93
    trä
    -0.93
     menutup
    -0.91
    🐛
    -0.91
     coercion
    -0.90
     expectancy
    -0.88
     crí
    -0.88
    derung
    -0.88
     then
    -0.87
     those
    -0.87
    POSITIVE LOGITS
     этого
    0.95
    撇
    0.94
     этой
    0.93
     accordo
    0.93
    k
    0.91
     graduación
    0.91
    かもしれない
    0.90
     himself
    0.90
     astounding
    0.89
    <h2>
    0.87
    Act Density 0.008%

    No Known Activations