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

    Neuronpedia

    INDEX
    Explanations

    javascript code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fprintf
    0.95
     NULL
    0.90
    printf
    0.86
    NULL
    0.83
     tunable
    0.75
     съ
    0.74
    perl
    0.73
     fprintf
    0.73
    threaded
    0.73
    Fermi
    0.72
    POSITIVE LOGITS
     !==
    1.23
     ===
    1.20
     localStorage
    1.20
    localStorage
    1.16
    ==="
    1.04
    toLocale
    1.00
     Promise
    0.94
     createdAt
    0.90
    !==
    0.87
     거예요
    0.87
    Act Density 0.152%

    No Known Activations