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

    Neuronpedia

    INDEX
    Explanations

    Amperes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sho
    0.80
     Ο
    0.73
     prête
    0.72
     Pim
    0.71
    嚯
    0.71
     dzie
    0.70
     پرویز
    0.69
     दिख
    0.68
     Protección
    0.67
     πάν
    0.67
    POSITIVE LOGITS
    ar
    0.95
    mas
    0.82
    arovski
    0.80
    lands
    0.78
    wells
    0.78
    neath
    0.76
    wearing
    0.75
     apertures
    0.75
    getti
    0.75
    coll
    0.74
    Act Density 0.000%

    No Known Activations