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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngừng
    -0.07
    力量
    -0.06
     rhetorical
    -0.06
     Я
    -0.06
    措施
    -0.06
    建设
    -0.06
    放在
    -0.06
     Logic
    -0.06
    (days
    -0.06
    στά
    -0.06
    POSITIVE LOGITS
    elines
    0.07
     $_
    0.06
    ujet
    0.06
    zoom
    0.06
     installing
    0.06
     ((_
    0.06
     *);↵↵
    0.06
     Augustine
    0.06
    (exception
    0.06
    �
    0.06
    Act Density 0.027%

    No Known Activations