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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    排序
    -0.07
     tú
    -0.07
    .SizeF
    -0.07
     operational
    -0.07
    知识产权
    -0.07
    ":↵↵
    -0.07
     este
    -0.07
    腭
    -0.06
    .ActionListener
    -0.06
    (element
    -0.06
    POSITIVE LOGITS
    صعب
    0.07
    不曾
    0.07
    قوى
    0.07
    bam
    0.07
    ⠇
    0.07
    /////
    0.07
     biz
    0.07
    _note
    0.07
     refine
    0.07
     Fiona
    0.06
    Act Density 0.000%

    No Known Activations