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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ауд
    -0.06
     Polar
    -0.06
    upt
    -0.06
     Saturday
    -0.06
     humano
    -0.06
    .”↵↵↵↵
    -0.06
    ”.
    -0.06
     axle
    -0.06
     годы
    -0.06
    userid
    -0.06
    POSITIVE LOGITS
     conjunction
    0.08
    زاده
    0.07
    udit
    0.06
    <stdio
    0.06
     contamination
    0.06
    glich
    0.06
    atica
    0.06
     عفش
    0.06
     veget
    0.06
    _ET
    0.06
    Act Density 0.005%

    No Known Activations