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

    Neuronpedia

    INDEX
    Explanations

    "but I can"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ender
    0.42
     electronics
    0.41
    September
    0.41
    Request
    0.41
     FileName
    0.41
     adsorption
    0.40
     May
    0.40
    Fee
    0.40
    Electronics
    0.40
     ()
    0.39
    POSITIVE LOGITS
    萂
    0.46
    ழிப்பு
    0.45
     Rimini
    0.40
    œ
    0.40
     ممل
    0.39
     radic
    0.39
     যে
    0.39
    ítő
    0.38
    arası
    0.38
     trailbl
    0.38
    Act Density 0.001%

    No Known Activations