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

    Neuronpedia

    INDEX
    Explanations

    Foster Cross-Functional Collaboration, Empathy, Creativity, Social, multi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AK
    2.22
    ON
    1.81
    EL
    1.77
    ara
    1.75
    Z
    1.75
    LOCK
    1.73
    IX
    1.71
    AA
    1.70
     automó
    1.69
    ot
    1.68
    POSITIVE LOGITS
    ת
    2.53
    里
    1.98
    ות
    1.91
    이라는
    1.85
    ব
    1.84
     akin
    1.82
    ة
    1.81
    ров
    1.80
    人材
    1.78
    د
    1.77
    Act Density 0.007%

    No Known Activations