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

    Neuronpedia

    INDEX
    Explanations

    Technical excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seks
    -0.07
    ojení
    -0.07
     kan
    -0.06
    try
    -0.06
    897
    -0.06
    Percentage
    -0.06
    しょ
    -0.06
    emplo
    -0.06
    板
    -0.06
    ин
    -0.06
    POSITIVE LOGITS
     ')↵
    0.07
     Lang
    0.06
    !',↵
    0.06
     Slash
    0.06
    ocument
    0.06
    (boolean
    0.06
    aguay
    0.06
    $title
    0.06
    öyle
    0.06
    itel
    0.06
    Act Density 0.072%

    No Known Activations