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

    Neuronpedia

    INDEX
    Explanations

    starting a comprehensive overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    1.41
    i
    1.16
    ]$.
    1.13
    +}$
    1.05
     또한
    0.95
    h
    0.92
    ર
    0.92
    TP
    0.90
    >
    0.89
    ف
    0.89
    POSITIVE LOGITS
     an
    1.23
     is
    1.19
     at
    1.18
     comes
    1.16
     a
    1.09
     chez
    1.05
     kommt
    1.05
     from
    1.05
     sobr
    1.04
     convuls
    1.03
    Act Density 0.555%

    No Known Activations