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

    Neuronpedia

    INDEX
    Explanations

    indicator titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ങ്ങ
    0.31
    圯
    0.29
     Persons
    0.29
    器官
    0.28
     नही
    0.27
     heretofore
    0.27
    陽
    0.27
    ಙ
    0.27
    件事情
    0.26
     Antigen
    0.26
    POSITIVE LOGITS
     casino
    0.42
     casinos
    0.41
    casino
    0.41
    pay
    0.37
    Casino
    0.37
    赌场
    0.37
     winnings
    0.37
     cashback
    0.35
     esports
    0.33
     FanDuel
    0.33
    Act Density 0.000%

    No Known Activations