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

    Neuronpedia

    INDEX
    Explanations

    e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мы
    0.55
    種類の
    0.53
    จัด
    0.51
     valmist
    0.49
     livers
    0.48
    гура
    0.47
    Мы
    0.47
     Зна
    0.47
    ຈ
    0.47
     magni
    0.47
    POSITIVE LOGITS
    Obviously
    0.41
    Appearance
    0.40
    Accuracy
    0.39
     calorías
    0.39
    ırım
    0.39
    €”
    0.39
    Conventional
    0.39
     cleaner
    0.38
    Iterations
    0.38
     Appearance
    0.38
    Act Density 0.082%

    No Known Activations