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

    Neuronpedia

    INDEX
    Explanations

    whatever, conversational, or specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lycée
    0.47
     Escola
    0.45
     libros
    0.45
     tunt
    0.44
     gimnas
    0.43
     shogun
    0.43
     livre
    0.43
     custard
    0.43
     rollers
    0.43
     sukh
    0.42
    POSITIVE LOGITS
    áte
    0.52
    effects
    0.47
    lemma
    0.45
    Definition
    0.43
    Moles
    0.43
     छोड़ा
    0.41
    LeftSide
    0.41
    Plane
    0.41
    प्र
    0.40
    Shape
    0.40
    Act Density 0.003%

    No Known Activations