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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divers
    -0.07
    otes
    -0.07
    Williams
    -0.06
     aprender
    -0.06
    Geometry
    -0.06
    uye
    -0.06
    aur
    -0.06
    ivering
    -0.06
    cola
    -0.06
     受
    -0.06
    POSITIVE LOGITS
     strugg
    0.07
    ddie
    0.07
     대상
    0.06
    .getActive
    0.06
    _LOOK
    0.06
     samostat
    0.06
     peacefully
    0.06
     predecessor
    0.06
    年に
    0.06
    ۵۰
    0.05
    Act Density 0.193%

    No Known Activations