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

    Neuronpedia

    INDEX
    Explanations

    cultural sensitivity and responsiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acket
    0.78
     Cab
    0.77
    aulay
    0.76
     rozwiązania
    0.76
     عشان
    0.75
    orithms
    0.75
    itude
    0.74
    ͘
    0.73
    azionali
    0.73
    راحة
    0.72
    POSITIVE LOGITS
     sensitivity
    0.98
     shock
    0.91
     Sensitivity
    0.89
     appropriation
    0.86
     choque
    0.82
     clash
    0.81
     transmission
    0.80
    Sensitivity
    0.80
     sensitive
    0.78
     competency
    0.77
    Act Density 0.051%

    No Known Activations