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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    god
    -0.07
     Dropdown
    -0.07
     точки
    -0.07
    (月
    -0.06
     uploading
    -0.06
    .parts
    -0.06
    ptr
    -0.06
     Slam
    -0.06
     Nap
    -0.06
     bleak
    -0.06
    POSITIVE LOGITS
    oded
    0.07
    ankind
    0.07
     lobby
    0.06
    ished
    0.06
    _levels
    0.06
     مدت
    0.06
    _upgrade
    0.06
    inae
    0.06
    ++]
    0.06
    upakan
    0.06
    Act Density 0.000%

    No Known Activations