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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drag
    -0.07
    datum
    -0.07
    。一
    -0.06
     manten
    -0.06
     viet
    -0.06
    Rew
    -0.06
    JsonValue
    -0.06
    /close
    -0.06
     Differences
    -0.06
     csak
    -0.06
    POSITIVE LOGITS
    وزه
    0.07
    gı
    0.07
    /bin
    0.06
     soil
    0.06
     mud
    0.06
     phận
    0.06
     explosive
    0.06
    _contents
    0.06
    illaume
    0.06
     choice
    0.06
    Act Density 0.140%

    No Known Activations