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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ascii
    -0.07
    >C
    -0.07
     Pacific
    -0.07
    .NewLine
    -0.06
    =*/
    -0.06
    树
    -0.06
     मश
    -0.06
     installer
    -0.06
    "]}
    -0.06
    -opacity
    -0.06
    POSITIVE LOGITS
    aways
    0.07
     Darren
    0.07
    닝
    0.06
    dings
    0.06
    owy
    0.06
    .ua
    0.06
    ายน
    0.06
    であり
    0.06
    'value
    0.06
    ництва
    0.06
    Act Density 0.095%

    No Known Activations