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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tjiwarl
    0.59
    ورٹی
    0.57
    नाइटेड
    0.57
    faulse
    0.56
    sadpoetry
    0.55
    িনবার্গ
    0.55
    󠁬
    0.55
    🛖
    0.55
    द्धाल
    0.54
    𒊩
    0.54
    POSITIVE LOGITS
     x
    0.83
    0.81
     T
    0.75
     C
    0.75
     +
    0.74
    -
    0.74
    _
    0.74
     \
    0.72
     t
    0.71
     D
    0.71
    Act Density 0.037%

    No Known Activations