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

    Neuronpedia

    INDEX
    Explanations

    website article snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    抬
    -0.07
    15
    -0.07
    _OF
    -0.07
     Gives
    -0.06
     eller
    -0.06
    那种
    -0.06
    sse
    -0.06
    bj
    -0.06
    Putting
    -0.06
    兹
    -0.06
    POSITIVE LOGITS
     account
    0.07
     taxp
    0.07
     ebook
    0.06
    عم
    0.06
     Native
    0.06
     "\">
    0.06
     single
    0.06
    \Annotation
    0.06
    (())↵
    0.06
     Aboriginal
    0.06
    Act Density 0.293%

    No Known Activations