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

    Neuronpedia

    INDEX
    Explanations

    increasingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     populaires
    0.50
     Hoping
    0.43
     populares
    0.42
    하려고
    0.42
    갱
    0.41
     гр
    0.40
     intentos
    0.39
     are
    0.39
     Collect
    0.39
     рее
    0.39
    POSITIVE LOGITS
    越來越
    0.51
    越来越多的
    0.46
     increasingly
    0.45
     zunehm
    0.44
    越来越
    0.44
     människor
    0.43
     becoming
    0.42
    越来越多
    0.42
     menemukan
    0.40
    คม
    0.39
    Act Density 0.013%

    No Known Activations