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

    Neuronpedia

    INDEX
    Explanations

    Friday and its surrounding context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    1.16
    fiction
    1.13
    ?
    1.00
    hedral
    0.96
    墘
    0.95
    };
    0.92
     of
    0.91
    ",
    0.91
     and
    0.90
    SIZE
    0.89
    POSITIVE LOGITS
     a
    1.34
    na
    1.19
    to
    1.13
     tourn
    1.10
    им
    1.08
    urón
    1.08
    ud
    1.05
    На
    1.05
    та
    1.03
    á
    1.03
    Act Density 0.002%

    No Known Activations