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

    Neuronpedia

    INDEX
    Explanations

    numbers and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excision
    0.55
    绡
    0.42
    有两个
    0.41
     orgasm
    0.41
    ینگ
    0.40
    有两种
    0.40
    ައި
    0.40
     insertion
    0.40
     bothers
    0.39
     utilises
    0.39
    POSITIVE LOGITS
    あくまで
    0.47
    居民
    0.45
    द्ध
    0.45
     ಸಂಖ್ಯ
    0.44
    г
    0.43
    മ്ബ
    0.42
    daily
    0.42
     প্রমুখ
    0.42
     dirigente
    0.41
    日々
    0.40
    Act Density 0.002%

    No Known Activations