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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hurt
    -0.07
    .keras
    -0.07
     пла
    -0.06
     Fifth
    -0.06
     müş
    -0.06
     واحدة
    -0.06
    冠
    -0.06
     lượng
    -0.06
    HG
    -0.06
     Lego
    -0.06
    POSITIVE LOGITS
    ())){↵
    0.07
    )*/↵
    0.06
    --------------↵
    0.06
    	help
    0.06
    tv
    0.06
     ド
    0.06
    Dod
    0.06
    ")),↵
    0.06
    [:,:
    0.06
    buttons
    0.06
    Act Density 0.001%

    No Known Activations