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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _blob
    -0.06
    plied
    -0.06
     Touch
    -0.06
    sprites
    -0.06
     logged
    -0.06
    _vc
    -0.06
    IVER
    -0.06
     notation
    -0.06
    .Popup
    -0.06
    ood
    -0.06
    POSITIVE LOGITS
    เหม
    0.08
     contenu
    0.07
    fc
    0.07
     temiz
    0.06
    عام
    0.06
    ucch
    0.06
     민주
    0.06
    „
    0.06
    μήμα
    0.06
     fc
    0.06
    Act Density 0.028%

    No Known Activations