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

    Neuronpedia

    INDEX
    Explanations

    granting abilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("""↵
    -0.07
    uyo
    -0.06
    [text
    -0.06
     Como
    -0.06
     XSS
    -0.06
    ADF
    -0.06
     晴
    -0.06
    elps
    -0.06
    ierrez
    -0.06
    confirm
    -0.06
    POSITIVE LOGITS
     captures
    0.07
     simple
    0.07
     kamp
    0.07
     upgraded
    0.07
     posix
    0.07
    ultiple
    0.06
    _same
    0.06
     gating
    0.06
     Neural
    0.06
     stout
    0.06
    Act Density 0.012%

    No Known Activations