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

    Neuronpedia

    INDEX
    Explanations

    conference statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quela
    0.98
    𝘦
    0.94
    ها
    0.90
     періо
    0.89
    as
    0.89
    ר
    0.87
     cote
    0.87
    quele
    0.84
    ৌম
    0.84
    ার
    0.84
    POSITIVE LOGITS
    また
    1.02
    न
    0.99
    p
    0.89
    e
    0.89
    পক্ষে
    0.87
    pod
    0.85
    site
    0.83
    tics
    0.82
    NumberOf
    0.82
    cad
    0.82
    Act Density 0.001%

    No Known Activations