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

    Neuronpedia

    INDEX
    Explanations

    exposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mousedown
    -0.06
     Simon
    -0.06
    Server
    -0.06
     bubbles
    -0.06
     bubble
    -0.06
     autoplay
    -0.06
     chocol
    -0.06
    ursor
    -0.06
     Moon
    -0.06
    لیم
    -0.06
    POSITIVE LOGITS
     exposed
    0.07
     terribly
    0.07
    �
    0.07
    brıs
    0.07
    .Ex
    0.07
    _Bar
    0.07
     confidently
    0.07
     SINGLE
    0.07
     الخام
    0.06
    ;"></
    0.06
    Act Density 0.009%

    No Known Activations