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

    Neuronpedia

    INDEX
    Explanations

    lists of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podcast
    0.49
    팁
    0.48
     टिप्स
    0.47
     pouce
    0.45
    おすすめです
    0.44
     anecdote
    0.44
     сове
    0.43
     তালিক
    0.43
     വിഷയ
    0.43
     dicas
    0.43
    POSITIVE LOGITS
     countries
    0.47
     Ländern
    0.46
    countries
    0.46
     \%(
    0.44
     étrangers
    0.42
     países
    0.42
    layered
    0.41
     стран
    0.41
     каждом
    0.40
    ab
    0.40
    Act Density 0.011%

    No Known Activations