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

    Neuronpedia

    INDEX
    Explanations

    child exploitation and welfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kurulum
    0.71
    ņas
    0.71
     Señor
    0.69
    इद
    0.68
    🗞
    0.68
    BASE
    0.67
    椭
    0.67
     ува
    0.66
    স্বামী
    0.66
     kişinin
    0.66
    POSITIVE LOGITS
    hood
    1.30
    swear
    1.23
     aged
    1.19
     prodig
    1.15
    🧒
    1.10
     ages
    1.08
     welfare
    1.08
    aged
    1.08
    agers
    1.07
    👦
    1.05
    Act Density 0.103%

    No Known Activations