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

    Neuronpedia

    INDEX
    Explanations

    Code and programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defeated
    -0.08
     Photos
    -0.08
    aterno
    -0.07
    _render
    -0.07
    avan
    -0.07
    minute
    -0.07
     arc
    -0.07
     confident
    -0.06
    itizen
    -0.06
     envisioned
    -0.06
    POSITIVE LOGITS
     Accordingly
    0.07
    เกษ
    0.06
    ۰۰۰
    0.06
    Plug
    0.06
     fakt
    0.06
    /QĐ
    0.06
    ném
    0.06
    Tem
    0.06
     vừa
    0.06
     SAND
    0.06
    Act Density 0.000%

    No Known Activations