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

    Neuronpedia

    INDEX
    Explanations

    itemize bullets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    »:
    1.18
    *:
    1.17
    `:
    1.17
    )：
    1.10
    !:
    1.07
    **:
    0.97
    ']:
    0.96
    >:
    0.96
    ”:
    0.95
    )):
    0.95
    POSITIVE LOGITS
    Those
    0.76
    দায়
    0.71
     Those
    0.68
     those
    0.67
     accomplishing
    0.66
    uales
    0.65
    That
    0.65
    ___
    0.64
     জুড়ে
    0.64
    those
    0.63
    Act Density 0.212%

    No Known Activations