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

    Neuronpedia

    INDEX
    Explanations

    rise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    族自治
    -0.07
    fred
    -0.07
    .mkdirs
    -0.07
    zeigt
    -0.07
     formData
    -0.07
     prophet
    -0.07
    浙
    -0.07
     Cree
    -0.07
     prostitut
    -0.07
     moet
    -0.07
    POSITIVE LOGITS
    .UnitTesting
    0.08
    �
    0.07
    pling
    0.07
    搪
    0.07
     весьма
    0.07
    .Game
    0.07
    .*
    0.06
    /core
    0.06
     почти
    0.06
     혹은
    0.06
    Act Density 0.006%

    No Known Activations