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

    Neuronpedia

    INDEX
    Explanations

    actions and their results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zunächst
    1.11
     senang
    1.03
     imprescindible
    1.02
     trio
    1.01
     práct
    0.95
     Janus
    0.94
     grundsätzlich
    0.93
     například
    0.92
     início
    0.92
     établissements
    0.92
    POSITIVE LOGITS
    ggg
    1.15
    ry
    1.11
    ly
    1.09
     Hwy
    1.04
    tec
    1.03
    1.03
    gggg
    1.02
    teile
    1.01
     دیگه
    1.00
     Pediatric
    0.99
    Act Density 0.005%

    No Known Activations