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

    Neuronpedia

    INDEX
    Explanations

    men and women

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ครับ
    0.88
    および
    0.87
    Learn
    0.85
     ครับ
    0.85
     şi
    0.85
     Cé
    0.79
    Read
    0.78
     Grazie
    0.77
     Learn
    0.76
     comedic
    0.75
    POSITIVE LOGITS
    Incidentally
    1.26
     Incidentally
    1.23
     Besides
    1.16
    According
    1.13
    Besides
    1.10
    Interestingly
    1.09
    1.08
     According
    1.08
    itherto
    1.08
     Interestingly
    1.04
    Act Density 0.003%

    No Known Activations