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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols, particularly related to matrices and linear algebra

    oai_token-act-pair · gemini-2.0-flash

    Code/Math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -1.12
    principalColumn
    -0.96
    expandindo
    -0.95
     MainAxisSize
    -0.93
     للمعارف
    -0.92
     ExecuteAsync
    -0.90
     незавершена
    -0.88
    ConstraintMaker
    -0.88
     nahilalakip
    -0.88
     kasarigan
    -0.88
    POSITIVE LOGITS
     
    0.53
     W
    0.53
    (
    0.51
    +
    0.51
     *
    0.51
    *
    0.51
    /
    0.50
     w
    0.50
     $
    0.49
    ro
    0.49
    Act Density 3.441%

    No Known Activations