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

    Neuronpedia

    INDEX
    Explanations

    mentioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oleh
    0.47
     when
    0.46
     ketika
    0.42
     όταν
    0.41
     depicted
    0.41
     quando
    0.41
     वहाँ
    0.41
     dentro
    0.41
     pelas
    0.40
     dedans
    0.40
    POSITIVE LOGITS
    usingCamera
    0.43
    lsulfanyl
    0.39
    どんどん
    0.38
    baren
    0.38
     Ё
    0.38
     ["[
    0.37
    知県
    0.36
     mogen
    0.36
     یق
    0.36
    ्रेन
    0.35
    Act Density 0.008%

    No Known Activations