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

    Neuronpedia

    INDEX
    Explanations

    relies on, blocking, equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вопросы
    0.45
     нового
    0.43
     Hỏi
    0.43
     preguntas
    0.41
    ابق
    0.41
    мены
    0.40
     Evaluación
    0.38
     вопросов
    0.38
     вопросам
    0.38
     questions
    0.38
    POSITIVE LOGITS
    yes
    0.71
    Yes
    0.68
     yes
    0.65
    YES
    0.64
     Yes
    0.63
     YES
    0.57
    lowest
    0.48
    stretched
    0.45
    justify
    0.44
    indeed
    0.44
    Act Density 0.000%

    No Known Activations