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

    Neuronpedia

    INDEX
    Explanations

    hidden mechanisms and passages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awk
    -0.09
     ഉപ
    -0.08
     distancing
    -0.08
     విన
    -0.08
    uhur
    -0.07
     lifestyle
    -0.07
     summarized
    -0.07
    adau
    -0.07
     વિર
    -0.07
    .flutter
    -0.07
    POSITIVE LOGITS
     clues
    0.09
    藏
    0.09
     indication
    0.09
     υπάρχει
    0.09
     escond
    0.09
     inscriptions
    0.08
    Masks
    0.08
    玄机
    0.08
     escon
    0.08
     реаг
    0.08
    Act Density 0.014%

    No Known Activations