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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诖
    -0.07
    еле
    -0.07
    (images
    -0.07
    浓厚
    -0.07
     These
    -0.07
    ��
    -0.07
    ethylene
    -0.06
    𝅎
    -0.06
    __()↵
    -0.06
     automobiles
    -0.06
    POSITIVE LOGITS
    Anal
    0.08
    圳
    0.07
    Ant
    0.07
    老化
    0.07
    되지
    0.07
     expansion
    0.07
    COND
    0.07
    Translate
    0.06
    Align
    0.06
     abandoned
    0.06
    Act Density 0.195%

    No Known Activations