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

    Neuronpedia

    INDEX
    Explanations

    emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olactone
    0.46
    imeric
    0.44
    गमेंट
    0.44
    を示す
    0.41
    ла
    0.41
    ढ़े
    0.41
     formalism
    0.41
    скоре
    0.41
    eword
    0.40
     Campylobacter
    0.40
    POSITIVE LOGITS
    ↵↵
    0.45
    ：
    0.43
    )
    0.43
    ✨
    0.41
     excellente
    0.40
    :
    0.40
    Avant
    0.39
    ).
    0.38
    4
    0.37
     yılında
    0.36
    Act Density 0.025%

    No Known Activations