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

    Neuronpedia

    INDEX
    Explanations

    defining variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㳳
    0.41
    ഴിലാ
    0.41
    Ⴖ
    0.40
    ITECT
    0.40
     tradicionales
    0.39
     );//
    0.38
    horst
    0.38
    ષ્ટ
    0.38
    uzten
    0.38
     illustrazione
    0.37
    POSITIVE LOGITS
     Answer
    0.79
    Answer
    0.74
    ANSWER
    0.64
     Ans
    0.61
     Answers
    0.59
    Ans
    0.59
    Show
    0.59
     Show
    0.58
     ANSWER
    0.57
    答案
    0.56
    Act Density 0.003%

    No Known Activations