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

    Neuronpedia

    INDEX
    Explanations

    you provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exemplifies
    1.04
     geomagnetic
    1.01
     undergoes
    0.99
    <unused1638>
    0.99
     unexplained
    0.98
     rallied
    0.98
     debuts
    0.98
     reaff
    0.98
     habitats
    0.96
    +](=
    0.96
    POSITIVE LOGITS
     your
    1.44
     yourself
    1.40
    your
    1.21
    yourself
    1.16
     Your
    1.13
    Your
    1.13
    你的
    1.11
    你
    1.05
     you
    0.97
     Yourself
    0.96
    Act Density 1.860%

    No Known Activations