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

    Neuronpedia

    INDEX
    Explanations

    first part of technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.49
    m
    0.45
    in
    0.40
    م
    0.36
    e
    0.34
    to
    0.33
    s
    0.32
    ed
    0.32
    ا
    0.31
     to
    0.31
    POSITIVE LOGITS
     அகற்ற
    0.31
     அவரது
    0.30
    なども
    0.30
     বলিউ
    0.29
     société
    0.29
     жовтня
    0.28
     proporcionan
    0.28
     comité
    0.28
     revisão
    0.28
    hishek
    0.28
    Act Density 0.422%

    No Known Activations