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

    Neuronpedia

    INDEX
    Explanations

    data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ocor
    0.45
    щением
    0.44
    Bienvenidos
    0.44
    uldades
    0.43
    brellas
    0.43
    ؤال
    0.41
    Accent
    0.41
    Descrição
    0.41
    pyridazin
    0.41
    ებენ
    0.41
    POSITIVE LOGITS
     boutique
    0.44
     shop
    0.43
    （
    0.43
     id
    0.42
     years
    0.42
     （
    0.42
     post
    0.41
     BE
    0.40
     Boutique
    0.40
     WER
    0.40
    Act Density 8.786%

    No Known Activations