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

    Neuronpedia

    INDEX
    Explanations

    acronyms and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()
    0.52
    ian
    0.49
     coffee
    0.47
    =""
    0.47
     could
    0.47
     Crowley
    0.46
     schedule
    0.45
     nutrition
    0.45
     can
    0.45
    ville
    0.45
    POSITIVE LOGITS
    রব
    0.45
    ροσ
    0.45
    ifers
    0.45
    న
    0.45
    ভ
    0.44
    oreg
    0.43
    ας
    0.43
    effectuer
    0.43
    Investing
    0.43
    たくさんの
    0.42
    Act Density 0.109%

    No Known Activations