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

    Neuronpedia

    INDEX
    Explanations

    gender identity or expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?)
    0.43
    大了
    0.42
     catastrophic
    0.39
     нему
    0.39
     spree
    0.39
     поступ
    0.39
    ПР
    0.38
     disasters
    0.38
     PPI
    0.38
     putea
    0.38
    POSITIVE LOGITS
     graced
    0.46
    ൽ
    0.46
     வரை
    0.45
    ოგ
    0.43
    が集
    0.43
    clazz
    0.43
     extol
    0.43
    Instant
    0.41
    ۗ
    0.41
     நவ
    0.41
    Act Density 0.004%

    No Known Activations