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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gow
    -0.07
     late
    -0.07
     womb
    -0.07
     SM
    -0.07
     pij
    -0.07
    官方
    -0.07
    forma
    -0.07
     ],↵↵
    -0.07
     */↵↵↵↵
    -0.07
     )
↵
    -0.06
    POSITIVE LOGITS
     getUser
    0.07
     schem
    0.07
    _assert
    0.07
    iven
    0.07
    consin
    0.07
     Publishers
    0.06
    gary
    0.06
    arris
    0.06
     Damascus
    0.06
    .Select
    0.06
    Act Density 0.162%

    No Known Activations