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

    Neuronpedia

    INDEX
    Explanations

    skincare or medical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ープ
    0.47
     output
    0.44
    बर्ग
    0.43
    Output
    0.43
     swear
    0.42
    श्याम
    0.42
     Output
    0.41
     क्लोरीन
    0.41
    สาย
    0.40
     लॉन्ग
    0.40
    POSITIVE LOGITS
     prides
    0.52
     prochains
    0.48
    AMM
    0.47
     quien
    0.46
    riv
    0.45
    oare
    0.44
     bienvenidas
    0.44
    ΟΥ
    0.44
     lum
    0.43
    ו
    0.43
    Act Density 0.002%

    No Known Activations