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

    Neuronpedia

    INDEX
    Explanations

    students and languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أغسطس
    0.67
     gota
    0.67
     ؟
    0.66
     Didn
    0.66
     Taking
    0.64
     \...
    0.64
     Was
    0.64
     使っ
    0.63
     こんな
    0.63
     ...
    0.61
    POSITIVE LOGITS
    alunos
    0.59
    친
    0.57
    worldwide
    0.56
    )`,
    0.55
    passport
    0.52
    SafeArea
    0.52
    (`<
    0.52
    <eos>
    0.52
    argar
    0.52
     personalised
    0.52
    Act Density 0.000%

    No Known Activations