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

    Neuronpedia

    INDEX
    Explanations

    applying concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metastable
    0.43
     Ugandan
    0.42
     convergence
    0.41
     Partition
    0.41
     Anxiety
    0.41
     Convergence
    0.40
     After
    0.40
     partition
    0.40
     Mythology
    0.40
     PTSD
    0.39
    POSITIVE LOGITS
     свет
    0.47
     адам
    0.46
     людини
    0.43
    Lewis
    0.43
     окружа
    0.43
     окружающей
    0.43
     ανθρώ
    0.42
     insanın
    0.42
     человека
    0.42
     науки
    0.41
    Act Density 0.002%

    No Known Activations