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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipe
    -0.07
     usuario
    -0.07
    sing
    -0.07
    (SQL
    -0.06
    urus
    -0.06
     storytelling
    -0.06
    overnment
    -0.06
    ,cljs
    -0.06
    'na
    -0.06
    nom
    -0.06
    POSITIVE LOGITS
     misunderstood
    0.07
     repealed
    0.07
    .Label
    0.06
    .addHandler
    0.06
    Finding
    0.06
    .fromRGBO
    0.06
     порядок
    0.06
     scares
    0.06
    ----------↵↵
    0.06
    .stub
    0.06
    Act Density 0.014%

    No Known Activations