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

    Neuronpedia

    INDEX
    Explanations

    font

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    winner
    -0.07
    回来
    -0.06
     aluno
    -0.06
    .constraint
    -0.06
    λευτα
    -0.06
    _atomic
    -0.06
     Іван
    -0.06
     공간
    -0.06
    lexer
    -0.06
     Land
    -0.06
    POSITIVE LOGITS
     types
    0.07
     privacy
    0.07
    dire
    0.07
    (filename
    0.07
    _Key
    0.06
    ších
    0.06
    Allocate
    0.06
    ]);
↵
    0.06
    FTP
    0.06
     tm
    0.06
    Act Density 0.017%

    No Known Activations