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

    Neuronpedia

    INDEX
    Explanations

    folder path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.88
    ה
    0.87
     parete
    0.78
    حق
    0.74
    ing
    0.71
    คุณ
    0.71
    ма
    0.71
     виправивши
    0.71
    เขา
    0.70
    imagenes
    0.70
    POSITIVE LOGITS
     Romney
    0.79
     pax
    0.75
     L
    0.75
    llä
    0.75
     IQ
    0.73
    ewhere
    0.73
    0.72
     Waltham
    0.71
     paws
    0.71
    lland
    0.71
    Act Density 0.000%

    No Known Activations