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

    Neuronpedia

    INDEX
    Explanations

    like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.16
    ak
    1.02
    ค์
    0.97
    क
    0.96
    tı
    0.91
    ف
    0.89
    t
    0.88
    ся
    0.86
    i
    0.84
    er
    0.82
    POSITIVE LOGITS
     który
    1.14
     който
    1.09
     혹은
    1.08
     Celui
    1.07
     pequeña
    1.06
     जिसमें
    1.05
     ठिकाणी
    1.05
     uscita
    1.02
    狯
    1.02
    揾
    1.02
    Act Density 0.029%

    No Known Activations