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

    Neuronpedia

    INDEX
    Explanations

    in a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పూర్తిగా
    0.42
     Newtonsoft
    0.39
     Tvam
    0.39
     嗯
    0.39
     }}=\
    0.38
     最近
    0.38
    Transaction
    0.38
    cevam
    0.38
    Xr
    0.38
    తో
    0.37
    POSITIVE LOGITS
    -
    0.36
    0.33
     defining
    0.31
     cuddling
    0.29
    \
    0.29
    o
    0.28
     the
    0.27
     sensory
    0.27
    бо
    0.26
    ния
    0.25
    Act Density 0.177%

    No Known Activations