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

    Neuronpedia

    INDEX
    Explanations

    chance to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.30
    these
    1.11
    that
    1.04
    sa
    1.03
    an
    1.02
    take
    1.02
    solutions
    1.02
    such
    1.01
    sche
    1.00
    <h2>
    0.98
    POSITIVE LOGITS
    ed
    1.27
    m
    1.08
     to
    1.02
    ৮
    1.01
    ৭০
    0.94
     lindas
    0.93
     chances
    0.93
    주고
    0.91
    ز
    0.91
    ير
    0.91
    Act Density 0.011%

    No Known Activations