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

    Neuronpedia

    INDEX
    Explanations

    parentheticals and dashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Although
    1.31
     Designed
    1.28
     Crafted
    1.21
     Demonstrated
    1.20
     Literally
    1.19
     Vì
    1.18
     Because
    1.18
     Launched
    1.15
     Được
    1.15
     Với
    1.13
    POSITIVE LOGITS
    _
    0.97
    /
    0.94
     or
    0.86
    -
    0.84
     beso
    0.77
    ↵
    0.77
     mal
    0.76
    --
    0.76
    ig
    0.76
     et
    0.76
    Act Density 0.101%

    No Known Activations