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

    Neuronpedia

    INDEX
    Explanations

    curated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reflux
    0.66
    warp
    0.66
     getValue
    0.63
     shortcut
    0.62
     short
    0.61
     pret
    0.60
     cling
    0.58
     cas
    0.57
     warp
    0.57
     clasp
    0.57
    POSITIVE LOGITS
     Cur
    1.05
    Cur
    1.00
    atorial
    0.95
    kurat
    0.94
     curricular
    0.93
    adoria
    0.92
     करिकुलम
    0.91
    த்தி
    0.90
    CUR
    0.88
    wellery
    0.88
    Act Density 0.002%

    No Known Activations