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

    Neuronpedia

    INDEX
    Explanations

    Arthur Penhaligon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     παιδιά
    0.39
     \<
    0.38
    ල්
    0.37
     Elabor
    0.37
     $<\
    0.37
    lde
    0.36
    elabor
    0.36
    よい
    0.35
     प्रती
    0.35
    adine
    0.35
    POSITIVE LOGITS
    GG
    0.40
    渠
    0.40
     Scenes
    0.38
    osk
    0.38
    Difference
    0.37
    瑭
    0.37
    izlik
    0.37
    alka
    0.36
    bets
    0.36
    ited
    0.36
    Act Density 0.001%

    No Known Activations