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

    Neuronpedia

    INDEX
    Explanations

    diagram characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    laughs
    -0.08
    	fp
    -0.08
    زة
    -0.07
    زين
    -0.07
     купить
    -0.07
     JPEG
    -0.07
    米
    -0.07
     לרכוש
    -0.07
    𐍄
    -0.07
     sư
    -0.07
    POSITIVE LOGITS
     dissolution
    0.07
     Battalion
    0.07
    淟
    0.07
    遗留
    0.07
     astro
    0.07
    Goal
    0.07
     Survival
    0.06
    MeshPro
    0.06
     Applied
    0.06
    ᐡ
    0.06
    Act Density 0.014%

    No Known Activations