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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насыщен
    0.42
     nyil
    0.40
    ショナル
    0.40
    ╋
    0.39
    ις
    0.39
     сиг
    0.39
     viss
    0.38
     обли
    0.38
     puiss
    0.38
     높
    0.38
    POSITIVE LOGITS
     fome
    0.42
    Independent
    0.42
    geq
    0.38
     runnable
    0.38
    //@
    0.37
     первых
    0.37
    False
    0.36
     egregious
    0.36
     কয়েকজন
    0.35
    preparation
    0.35
    Act Density 0.016%

    No Known Activations