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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.44
    на
    0.44
    ة
    0.40
     Abbiamo
    0.38
    ك
    0.38
    е
    0.38
    ный
    0.35
    의
    0.35
    ية
    0.34
    Have
    0.34
    POSITIVE LOGITS
    \
    0.31
     financ
    0.31
     kilowatt
    0.30
    +.
    0.29
     conno
    0.28
     globules
    0.27
     medicine
    0.27
     doctorate
    0.27
     بوت
    0.27
     more
    0.27
    Act Density 0.376%

    No Known Activations