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

    Neuronpedia

    INDEX
    Explanations

    err/REFERER

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ckill
    -0.07
    birth
    -0.07
     fulfill
    -0.07
    (fullfile
    -0.07
    ฏ
    -0.07
    靥
    -0.07
    孽
    -0.07
     dương
    -0.07
     suç
    -0.07
     sayı
    -0.07
    POSITIVE LOGITS
     Ten
    0.07
    _needed
    0.07
     satin
    0.07
     Albany
    0.07
     barriers
    0.07
    0.07
     Always
    0.07
     Delegate
    0.07
    /entity
    0.07
    苛
    0.07
    Act Density 0.002%

    No Known Activations