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

    Neuronpedia

    INDEX
    Explanations

    additional information, documentation, licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ilə
    0.41
     suất
    0.41
     exodus
    0.38
     मुहैया
    0.38
     với
    0.38
    могою
    0.37
    骛
    0.37
     هون
    0.37
     agreement
    0.36
    :=\
    0.36
    POSITIVE LOGITS
    中国人
    0.43
    acker
    0.42
    ponsors
    0.42
     فهر
    0.40
    acres
    0.39
    AVY
    0.39
    FO
    0.39
     Rejo
    0.38
    ACES
    0.38
    FAC
    0.38
    Act Density 0.002%

    No Known Activations