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

    Neuronpedia

    INDEX
    Explanations

    look out for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.64
    vin
    0.62
    la
    0.60
    ra
    0.59
    astics
    0.58
     lä
    0.58
     I
    0.57
    apa
    0.55
     treino
    0.54
     Lä
    0.54
    POSITIVE LOGITS
    اه
    0.70
    の新
    0.70
    ﻒ
    0.67
    ﹉
    0.65
    ا
    0.64
    ২
    0.63
    માં
    0.62
     signs
    0.62
    是否有
    0.62
    الد
    0.62
    Act Density 0.070%

    No Known Activations