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

    Neuronpedia

    INDEX
    Explanations

    cells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _THE
    -0.07
    _multiple
    -0.06
    ोप
    -0.06
     nxt
    -0.06
    onal
    -0.06
    ницу
    -0.06
    вок
    -0.06
     opcode
    -0.06
    ậu
    -0.06
    iets
    -0.06
    POSITIVE LOGITS
     regardless
    0.07
    [M
    0.06
     Χ
    0.06
     pepp
    0.06
    reported
    0.06
    واره
    0.06
     tapi
    0.06
     vaginal
    0.06
    definitions
    0.06
    --)
↵
    0.06
    Act Density 0.033%

    No Known Activations