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

    Neuronpedia

    INDEX
    Explanations

    Oracle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    between
    -0.08
     investing
    -0.07
    .Middle
    -0.07
     happier
    -0.07
    gaard
    -0.06
    starttime
    -0.06
    umph
    -0.06
    だよ
    -0.06
     iw
    -0.06
     peel
    -0.06
    POSITIVE LOGITS
     topLeft
    0.07
    _Close
    0.07
     krat
    0.06
    413
    0.06
     lég
    0.06
    GestureRecognizer
    0.06
     res
    0.06
     straně
    0.06
    favicon
    0.06
    二二
    0.06
    Act Density 0.002%

    No Known Activations