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

    Neuronpedia

    INDEX
    Explanations

    curring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )</
    -0.07
    don
    -0.06
    .toolStrip
    -0.06
    -block
    -0.06
    dos
    -0.06
    दम
    -0.06
    應
    -0.06
     wnd
    -0.06
     matriz
    -0.06
    нуться
    -0.06
    POSITIVE LOGITS
     nghe
    0.06
    زان
    0.06
     consuming
    0.06
     필
    0.06
    neighbors
    0.06
    크
    0.06
    kových
    0.06
     postage
    0.06
    iazza
    0.06
     nové
    0.06
    Act Density 0.000%

    No Known Activations