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

    Neuronpedia

    INDEX
    Explanations

    social norms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disrupt
    0.52
     disruption
    0.47
     losses
    0.46
    0.46
     challenges
    0.45
    -
    0.44
     massage
    0.44
    ಲ
    0.43
     impact
    0.43
     its
    0.43
    POSITIVE LOGITS
    ကိုယ်
    0.51
     বয়সী
    0.50
    இதில்
    0.49
     Negotiations
    0.48
    izedBox
    0.48
    澳大利
    0.48
     Конгрегация
    0.48
    बाट
    0.47
     Zeitraum
    0.47
     বয়সী
    0.47
    Act Density 0.010%

    No Known Activations