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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    抑
    -0.07
     cevap
    -0.06
    ffen
    -0.06
     Linear
    -0.06
    ural
    -0.06
     در
    -0.06
    .pow
    -0.06
    隐
    -0.06
     editors
    -0.06
     editing
    -0.06
    POSITIVE LOGITS
     للس
    0.07
     unin
    0.07
     Dutch
    0.07
    Americans
    0.06
    /gcc
    0.06
    [T
    0.06
     peoples
    0.06
     EAR
    0.06
     Vienna
    0.06
     fueled
    0.06
    Act Density 0.000%

    No Known Activations