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

    Neuronpedia

    INDEX
    Explanations

    not an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を楽しむ
    0.43
    问题
    0.42
     или
    0.40
     trivial
    0.40
     yoki
    0.40
    ॑
    0.39
    或
    0.39
     openly
    0.39
     пробле
    0.38
    衅
    0.38
    POSITIVE LOGITS
     affiliated
    0.49
    affiliated
    0.46
     Offering
    0.46
     مشار
    0.46
     profesional
    0.45
    പ്പെട്ട്
    0.44
     participating
    0.43
     WIP
    0.43
     enrolled
    0.43
     expertos
    0.42
    Act Density 0.066%

    No Known Activations