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

    Neuronpedia

    INDEX
    Explanations

    programming and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mortality
    -0.07
    .idea
    -0.07
     provinces
    -0.07
     Sunday
    -0.06
     minds
    -0.06
     Film
    -0.06
     Amerika
    -0.06
     Diego
    -0.06
     COL
    -0.06
    uma
    -0.06
    POSITIVE LOGITS
    тів
    0.07
    (ob
    0.07
     обличчя
    0.07
    .rdf
    0.07
    提高
    0.06
     unheard
    0.06
    _RESERVED
    0.06
    .promise
    0.06
    líč
    0.06
    SQLite
    0.06
    Act Density 0.099%

    No Known Activations