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

    Neuronpedia

    INDEX
    Explanations

    unfinished clauses and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \...
    0.95
    …
    0.76
    ...),
    0.72
    ...
    0.70
    ,
    0.70
    ...');
    0.67
    \
    0.67
    ...')
    0.66
    들이
    0.65
    …?
    0.65
    POSITIVE LOGITS
    sigh
    1.61
    they
    1.48
    and
    1.42
    there
    1.42
    this
    1.40
    They
    1.38
    There
    1.35
    This
    1.34
    You
    1.32
    It
    1.32
    Act Density 0.162%

    No Known Activations