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

    Neuronpedia

    INDEX
    Explanations

    constitution, fall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    га
    0.48
    ین
    0.46
    اں
    0.46
    ال
    0.45
    oretically
    0.42
     expiresIn
    0.42
    cribed
    0.41
    av
    0.40
    ام
    0.40
    卄
    0.40
    POSITIVE LOGITS
    এটি
    0.42
    нга
    0.40
     sätt
    0.40
     sayıda
    0.39
    POL
    0.39
     διαδικ
    0.38
    जीटी
    0.38
    mtq
    0.38
     entspricht
    0.37
    benar
    0.36
    Act Density 0.018%

    No Known Activations