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

    Neuronpedia

    INDEX
    Explanations

    AI chatbots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ('
    0.45
    pcm
    0.45
    >
    0.43
     ">
    0.42
    ।"
    0.42
    riss
    0.42
     発
    0.41
    ochastic
    0.41
     அதே
    0.40
    Categoria
    0.40
    POSITIVE LOGITS
     stér
    0.44
     때문
    0.43
     fatto
    0.42
     fumar
    0.42
     disturbs
    0.42
     sueños
    0.41
     rango
    0.41
     opérateurs
    0.41
     dham
    0.40
    🧺
    0.40
    Act Density 0.001%

    No Known Activations