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

    Neuronpedia

    INDEX
    Explanations

    streaming bandwidth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.55
    n
    0.52
    ř
    0.49
    it
    0.48
    urnal
    0.48
     pobl
    0.48
    an
    0.47
    abot
    0.46
    r
    0.46
     Romana
    0.46
    POSITIVE LOGITS
    線を
    0.43
     microphones
    0.41
    Kes
    0.41
     μου
    0.41
     kes
    0.40
     ERIC
    0.40
     голов
    0.40
    お客様
    0.39
     autistic
    0.39
     arquivos
    0.39
    Act Density 0.001%

    No Known Activations