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

    Neuronpedia

    INDEX
    Explanations

    pedagogy and pediatrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.55
    p
    1.31
    is
    1.28
    ール
    1.25
    am
    1.19
    ay
    1.18
    o
    1.18
    ב
    1.16
    อง
    1.10
     the
    1.09
    POSITIVE LOGITS
    ва
    1.29
    이랑
    1.23
    ,~
    1.09
     pedag
    1.07
     불구하고
    1.07
     péd
    1.05
     PED
    1.05
    Ped
    1.02
    ۰
    1.02
     педагоги
    1.02
    Act Density 0.003%

    No Known Activations