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

    Neuronpedia

    INDEX
    Explanations

    storage, SSD, data, queues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Durante
    0.41
     student
    0.40
     concomitant
    0.40
     gas
    0.39
     criterion
    0.39
     газо
    0.38
     presidency
    0.38
     unable
    0.38
     licenciatura
    0.37
     '(
    0.37
    POSITIVE LOGITS
    ඉ
    0.44
    𝔰
    0.43
    ቐ
    0.43
    𝗯
    0.43
     ກ
    0.41
    焐
    0.41
    𝗄
    0.40
    мышлен
    0.40
    Aes
    0.40
    푅
    0.39
    Act Density 0.001%

    No Known Activations