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

    Neuronpedia

    INDEX
    Explanations

    Email headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Como
    -0.07
     خشک
    -0.06
     Loving
    -0.06
     四
    -0.06
    /W
    -0.06
     Bern
    -0.06
     justo
    -0.06
     чет
    -0.06
    _mc
    -0.06
    .realpath
    -0.06
    POSITIVE LOGITS
     hind
    0.07
    _EVENT
    0.06
    рож
    0.06
     split
    0.06
    celed
    0.06
    essay
    0.06
    ận
    0.06
    _Anim
    0.06
     tl
    0.06
    ;-
    0.06
    Act Density 0.006%

    No Known Activations