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

    Neuronpedia

    INDEX
    Explanations

    correctly, properly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مرک
    -0.06
    erin
    -0.06
     =========================================================================
    -0.06
     گذشته
    -0.06
    ленно
    -0.06
    ازند
    -0.06
    映
    -0.06
    -Б
    -0.06
     frogs
    -0.06
     लगत
    -0.06
    POSITIVE LOGITS
    िसस
    0.07
    English
    0.07
    Torrent
    0.07
    .If
    0.07
    (android
    0.07
    Dirty
    0.06
    (Board
    0.06
     tolik
    0.06
    .isActive
    0.06
     lesbians
    0.06
    Act Density 0.022%

    No Known Activations