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

    Neuronpedia

    INDEX
    Explanations

    Embryo development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laws
    -0.07
     на
    -0.07
     Worlds
    -0.07
     aren
    -0.07
     media
    -0.07
     kitchens
    -0.06
     forget
    -0.06
     nine
    -0.06
     sometimes
    -0.06
    **↵
    -0.06
    POSITIVE LOGITS
     FileReader
    0.07
    allet
    0.07
    RegularExpression
    0.06
     DataBase
    0.06
    bindValue
    0.06
    prompt
    0.06
     Ecuador
    0.06
    coes
    0.06
    agit
    0.06
     paddingLeft
    0.06
    Act Density 0.038%

    No Known Activations