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

    Neuronpedia

    INDEX
    Explanations

    Coding and data errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fixed
    -0.07
     Communication
    -0.07
    /ph
    -0.07
    categoryId
    -0.07
    ################################
    -0.07
    .Syntax
    -0.06
    大家一起
    -0.06
    内で
    -0.06
     Sark
    -0.06
    🐀
    -0.06
    POSITIVE LOGITS
     EU
    0.08
    仅为
    0.07
     title
    0.07
    (U
    0.07
     önemli
    0.07
     oferta
    0.07
    (title
    0.07
     Tucson
    0.06
    ToAdd
    0.06
     unpl
    0.06
    Act Density 0.083%

    No Known Activations