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

    Neuronpedia

    INDEX
    Explanations

    AmsiScanBuffer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ཟ
    0.40
     QuantityOnHand
    0.40
    ப்பின்
    0.40
    (?)
    0.39
     봅시다
    0.39
    硣
    0.39
     похађа
    0.38
     अर्
    0.38
     "=",
    0.38
     исправ
    0.38
    POSITIVE LOGITS
     Am
    0.48
    icol
    0.48
    Am
    0.47
     am
    0.44
    امه
    0.43
    äm
    0.42
     amu
    0.40
    jord
    0.39
    came
    0.39
     discredit
    0.39
    Act Density 0.011%

    No Known Activations