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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heartbreaking
    -0.07
     scrambled
    -0.07
    .lv
    -0.06
    Ops
    -0.06
    devil
    -0.06
     Rice
    -0.06
    ="--
    -0.06
    .ic
    -0.06
    048
    -0.06
    .hu
    -0.06
    POSITIVE LOGITS
     ornaments
    0.07
     impro
    0.07
     restrict
    0.06
    emer
    0.06
     infancy
    0.06
    lük
    0.06
    人は
    0.06
     Imper
    0.06
    modelo
    0.06
    mtx
    0.06
    Act Density 0.003%

    No Known Activations