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

    Neuronpedia

    INDEX
    Explanations

    NO guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caído
    0.85
    진
    0.77
    적인
    0.77
     version
    0.73
     versión
    0.71
     sequência
    0.71
     margarita
    0.71
    ным
    0.71
     ý
    0.70
     matrícula
    0.68
    POSITIVE LOGITS
    الش
    0.78
    biotics
    0.76
    ie
    0.74
    alcool
    0.74
    i
    0.74
     Assoc
    0.72
     อะไร
    0.71
    irts
    0.71
    prache
    0.71
    oglycos
    0.71
    Act Density 0.002%

    No Known Activations