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

    Neuronpedia

    INDEX
    Explanations

    offer support and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Consult
    0.87
    Asimismo
    0.81
    続け
    0.80
     परामर्श
    0.79
     consente
    0.74
    Consult
    0.74
     Toutefois
    0.74
     याचिका
    0.73
     Asimismo
    0.73
     Visa
    0.71
    POSITIVE LOGITS
     굉장히
    0.76
    すごく
    0.72
     elementów
    0.72
    めっちゃ
    0.70
     dimensión
    0.68
     najważ
    0.66
     نہایت
    0.66
     cái
    0.66
     muchísimo
    0.65
     ridiculously
    0.65
    Act Density 0.239%

    No Known Activations