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

    Neuronpedia

    INDEX
    Explanations

    hydrogen gas, developing prototypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     competición
    0.62
     canh
    0.58
     ouvir
    0.57
     እንኳን
    0.57
    が通販
    0.56
     Teor
    0.55
     божомолдор
    0.54
     empresas
    0.53
     собы
    0.53
     UWGM
    0.53
    POSITIVE LOGITS
    t
    0.57
     §
    0.55
    Child
    0.52
    child
    0.50
     (§
    0.49
    L
    0.48
    a
    0.48
     as
    0.48
    §
    0.47
     informed
    0.46
    Act Density 0.001%

    No Known Activations