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

    Neuronpedia

    INDEX
    Explanations

    paper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UN
    -0.07
     blend
    -0.07
    axes
    -0.07
     chef
    -0.07
    Ｗ
    -0.07
    ACH
    -0.07
    トン
    -0.07
     corridor
    -0.07
    ocus
    -0.07
    ICON
    -0.06
    POSITIVE LOGITS
     caract
    0.08
     перв
    0.08
     empir
    0.08
     jelly
    0.08
     derp
    0.07
     kter
    0.07
     paper
    0.07
     probs
    0.07
    .reporting
    0.07
    .scalatest
    0.07
    Act Density 0.021%

    No Known Activations