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

    Neuronpedia

    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肟
    -0.08
     histogram
    -0.08
     butter
    -0.07
    オス
    -0.07
    že
    -0.07
    riding
    -0.07
    фт
    -0.07
    ross
    -0.07
    Greg
    -0.07
    .collections
    -0.06
    POSITIVE LOGITS
    DATES
    0.07
     Helpers
    0.07
    RELEASE
    0.07
    >');↵↵
    0.07
     DOWNLOAD
    0.07
     Statement
    0.07
     #"
    0.07
    轮回
    0.06
     З
    0.06
    ']
↵
↵
    0.06
    Act Density 0.001%

    No Known Activations