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

    Neuronpedia

    INDEX
    Explanations

    Identifiers/citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -described
    -0.07
    inte
    -0.07
     wäre
    -0.06
    gorithms
    -0.06
    OutOf
    -0.06
     myList
    -0.06
    Ан
    -0.06
    apist
    -0.06
    Пол
    -0.06
    mb
    -0.06
    POSITIVE LOGITS
     hablar
    0.07
     Bollywood
    0.07
     xpath
    0.06
     thriving
    0.06
    所属
    0.06
     obtaining
    0.06
     okamž
    0.06
    ющей
    0.06
    covery
    0.06
    655
    0.06
    Act Density 0.004%

    No Known Activations