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

    Neuronpedia

    INDEX
    Explanations

    days of the week / item issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kesin
    0.80
    ?:
    0.80
    ?",
    0.80
    …,
    0.79
     ?",
    0.78
     মহার
    0.76
     necesita
    0.75
    ...",
    0.75
    ();//
    0.75
    orat
    0.75
    POSITIVE LOGITS
    ↵↵
    1.85
    ↵↵↵
    1.22
    ↵↵↵↵
    1.16
    ↵↵↵↵↵
    1.11
    <start_of_image>
    1.03
    ↵↵↵↵↵↵
    0.98
    ↵
    0.95
    \\
    0.95
    )
    0.91
    .
    0.86
    Act Density 0.183%

    No Known Activations