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

    Neuronpedia

    INDEX
    Explanations

    Glass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     часом
    -0.07
     BY
    -0.06
    FY
    -0.06
    ーチ
    -0.06
    щий
    -0.06
     smokers
    -0.06
    Reading
    -0.06
    hores
    -0.06
    mul
    -0.06
     rating
    -0.06
    POSITIVE LOGITS
    _capability
    0.07
    ”，
    0.07
     sexle
    0.06
    _ISR
    0.06
     Newly
    0.06
    dataGridView
    0.06
     lamp
    0.06
     disturbance
    0.06
    来说
    0.06
    _favorite
    0.06
    Act Density 0.000%

    No Known Activations