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

    Neuronpedia

    INDEX
    Explanations

    started

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =query
    -0.07
     tackling
    -0.07
     glean
    -0.06
    empt
    -0.06
    _strip
    -0.06
    _cal
    -0.06
    =options
    -0.06
    (period
    -0.06
     갤
    -0.06
    ตรวจ
    -0.06
    POSITIVE LOGITS
     кредит
    0.07
    uencia
    0.06
     stripper
    0.06
    otty
    0.06
     높
    0.06
    ेक
    0.06
     издел
    0.06
    蛛
    0.06
    -important
    0.06
    ORIA
    0.06
    Act Density 0.006%

    No Known Activations