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

    Neuronpedia

    INDEX
    Explanations

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Teknologi
    0.48
     Tsun
    0.47
     Bildung
    0.47
    纤维
    0.46
    áticas
    0.46
    Посилання
    0.45
    एलबी
    0.45
    िलो
    0.44
     DOOR
    0.44
     sociable
    0.43
    POSITIVE LOGITS
     ele
    0.49
     mechanized
    0.49
     pipes
    0.48
    選
    0.48
     infinites
    0.46
    es
    0.46
     judges
    0.45
     elects
    0.44
    i
    0.44
    先
    0.44
    Act Density 0.004%

    No Known Activations