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

    Neuronpedia

    INDEX
    Explanations

    AI, tool, code, data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    哈哈哈
    0.45
     unavailable
    0.43
    脸色
    0.42
     entrev
    0.42
    哈哈
    0.41
     disponibilité
    0.39
     برخور
    0.39
    फरी
    0.39
     😂😂
    0.38
    ර්ධ
    0.38
    POSITIVE LOGITS
    connection
    0.46
    link
    0.45
     beg
    0.44
    äub
    0.42
    ruption
    0.41
     ইসলামিক
    0.40
    thers
    0.39
    Islamic
    0.39
    login
    0.39
    mes
    0.39
    Act Density 0.001%

    No Known Activations