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

    Neuronpedia

    INDEX
    Explanations

    sexual violence and harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mahi
    0.48
     комплекс
    0.45
    aéroport
    0.44
    微微
    0.43
     বিমানবন্দ
    0.43
    мога
    0.42
    esu
    0.41
     aerosols
    0.41
    Lung
    0.41
    桥
    0.41
    POSITIVE LOGITS
     notre
    0.61
     動
    0.45
     کئے
    0.43
    udence
    0.43
     आपका
    0.43
     संभावना
    0.42
    さえ
    0.42
     Religion
    0.42
     Loc
    0.42
    ┛
    0.42
    Act Density 2.230%

    No Known Activations