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

    Neuronpedia

    INDEX
    Explanations

    scientific reclassification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    墙上
    -0.07
    訪れ
    -0.07
     starting
    -0.07
     võ
    -0.07
    /,↵
    -0.06
    [t
    -0.06
    ßen
    -0.06
    ﲒ
    -0.06
     ($
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
     redraw
    0.08
     מבוסס
    0.08
    GAME
    0.08
     Angus
    0.07
     hdf
    0.07
    $obj
    0.07
    Rail
    0.07
    猕
    0.07
     MESSAGE
    0.07
    payments
    0.07
    Act Density 0.021%

    No Known Activations