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

    Neuronpedia

    INDEX
    Explanations

    spinning object, evil AI, blind man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    illance
    1.21
     urbanization
    1.21
    лка
    1.20
    idation
    1.18
    esterno
    1.18
     calorimetry
    1.16
    paround
    1.16
    igation
    1.15
    itism
    1.15
    icate
    1.13
    POSITIVE LOGITS
    ار
    1.55
    s
    1.30
    ों
    1.20
     multiplets
    1.20
    לא
    1.19
    כ
    1.14
    A
    1.12
    \{
    1.10
    คุณ
    1.08
    م
    1.08
    Act Density 0.195%

    No Known Activations