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

    Neuronpedia

    INDEX
    Explanations

    local LGBTQ+ mental health resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    開
    0.48
    符号
    0.47
     ganzen
    0.47
     symbols
    0.46
     dingen
    0.46
    ra
    0.46
    ers
    0.45
     ج
    0.45
    return
    0.45
     icons
    0.44
    POSITIVE LOGITS
    iscilla
    0.53
     سمجھتے
    0.50
     استح
    0.44
    獼
    0.43
    مارسة
    0.42
     दोन्ही
    0.42
    ździer
    0.42
     적용
    0.41
     whichever
    0.41
     محاس
    0.41
    Act Density 0.001%

    No Known Activations