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

    Neuronpedia

    INDEX
    Explanations

    detecting/sensing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clave
    -0.06
    resar
    -0.06
     Horse
    -0.06
    avored
    -0.06
     Basin
    -0.06
     water
    -0.06
     zone
    -0.06
    _MODULES
    -0.06
     zones
    -0.06
    izona
    -0.06
    POSITIVE LOGITS
     dorm
    0.08
    各种
    0.07
    &action
    0.07
     Dorm
    0.07
    ，便
    0.07
     특
    0.07
     عنوان
    0.07
     sightings
    0.06
    うん
    0.06
    )((
    0.06
    Act Density 0.018%

    No Known Activations