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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dangerously
    -0.06
     матери
    -0.06
     Lid
    -0.06
    ฟร
    -0.06
     рецепт
    -0.06
    chas
    -0.06
     Kiş
    -0.06
    .dispatch
    -0.06
    少し
    -0.05
    菜
    -0.05
    POSITIVE LOGITS
     //(
    0.07
     Tanrı
    0.07
    ENGINE
    0.07
     Wooden
    0.07
     sm
    0.07
    standen
    0.06
    .weixin
    0.06
    acak
    0.06
    	wc
    0.06
    Neil
    0.06
    Act Density 0.033%

    No Known Activations