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

    Neuronpedia

    INDEX
    Explanations

    discussing risks and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enzymatic
    0.42
     Ciência
    0.41
     acre
    0.41
    ípios
    0.40
    化
    0.39
    蔬
    0.39
    ínsula
    0.39
     Clínica
    0.38
     دفع
    0.38
     Science
    0.37
    POSITIVE LOGITS
     क्‍
    0.44
    Marathi
    0.44
    Party
    0.43
    ប៉
    0.42
    報酬
    0.41
    party
    0.41
    籐
    0.40
    锃
    0.40
     गंभीरता
    0.40
    टाइ
    0.40
    Act Density 0.001%

    No Known Activations