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

    Neuronpedia

    INDEX
    Explanations

    coping mechanisms like mindfulness, yoga, talking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lula
    0.66
     unsupervised
    0.65
     women
    0.64
     pods
    0.63
     ženy
    0.62
    iling
    0.62
    uição
    0.61
     itens
    0.61
     आशीष
    0.61
    條件
    0.61
    POSITIVE LOGITS
     спорта
    0.82
     tinh
    0.70
     الرياض
    0.69
     maintain
    0.68
     journalism
    0.67
     térmica
    0.66
     engraving
    0.66
    XRD
    0.66
    Tinh
    0.65
     diversification
    0.64
    Act Density 0.160%

    No Known Activations