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

    Neuronpedia

    INDEX
    Explanations

    providing or asking for reasons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    珍
    -0.07
    县
    -0.07
    ैश
    -0.06
    使用
    -0.06
    jedn
    -0.06
     Wikispecies
    -0.06
    吃
    -0.06
    議
    -0.06
    ρυ
    -0.06
    Observer
    -0.06
    POSITIVE LOGITS
    ]={
    0.06
     home
    0.06
    WINDOW
    0.06
     fiscal
    0.06
    )/
    0.06
    {lng
    0.06
    (ele
    0.06
     flown
    0.06
     ف
    0.06
     کام
    0.06
    Act Density 0.008%

    No Known Activations