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

    Neuronpedia

    INDEX
    Explanations

    arguably create Deep Learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ótimo
    0.42
    赢
    0.42
    Adding
    0.41
    టా
    0.41
     adicionar
    0.41
    秉
    0.41
     acrescent
    0.40
    赸
    0.40
     Jú
    0.40
    чне
    0.39
    POSITIVE LOGITS
    agic
    0.39
    leg
    0.38
    wati
    0.38
    esh
    0.37
    zl
    0.37
    MILLISE
    0.37
    mj
    0.36
    wrapp
    0.36
     unusable
    0.36
    fruit
    0.35
    Act Density 0.004%

    No Known Activations