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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Always
    -0.07
    Mas
    -0.07
     آنچه
    -0.07
     приб
    -0.07
     않을
    -0.07
    OVER
    -0.06
     프로
    -0.06
     interceptions
    -0.06
    optic
    -0.06
     doğr
    -0.06
    POSITIVE LOGITS
    xfb
    0.06
    amı
    0.06
    istringstream
    0.06
     nan
    0.06
     whistlebl
    0.06
     s
    0.06
    ocl
    0.06
     fic
    0.06
    Freedom
    0.05
    .GetAxis
    0.05
    Act Density 0.049%

    No Known Activations