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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otes
    -0.07
    ediator
    -0.07
    SceneManager
    -0.06
    iendo
    -0.06
    $/)
    -0.06
     note
    -0.06
     highlighted
    -0.06
    ollen
    -0.06
    抬
    -0.06
    遗
    -0.06
    POSITIVE LOGITS
    ेण
    0.07
    .Configure
    0.07
    olecules
    0.06
    SPELL
    0.06
    .Decode
    0.06
    _Close
    0.06
     खड
    0.06
     maté
    0.06
    ۱۹۵
    0.06
    BSITE
    0.06
    Act Density 0.259%

    No Known Activations