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

    Neuronpedia

    INDEX
    Explanations

    code and programming structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    years
    0.47
    zed
    0.45
    ોર્ટ
    0.44
    ed
    0.43
     üt
    0.41
     أساس
    0.40
     became
    0.39
     the
    0.39
    the
    0.38
     Years
    0.38
    POSITIVE LOGITS
     mogą
    0.40
    Adams
    0.39
    蒞
    0.38
     Sito
    0.38
    ង្
    0.36
    重要な
    0.36
    ართველ
    0.35
     gonflement
    0.35
     Développement
    0.35
     pyramidal
    0.35
    Act Density 0.042%

    No Known Activations