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

    Neuronpedia

    INDEX
    Explanations

    parent school events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     エネルギー
    0.43
    ريح
    0.42
    ਿਆਂ
    0.41
    اده
    0.40
    ेटा
    0.39
     विद्यार्थी
    0.38
     एनी
    0.37
     дітей
    0.37
    ಖ
    0.36
     давайте
    0.36
    POSITIVE LOGITS
    项目
    0.48
    individual
    0.47
    project
    0.46
    inform
    0.46
     individuales
    0.44
     Individual
    0.44
    Individual
    0.43
    mvc
    0.43
    sm
    0.42
    open
    0.41
    Act Density 0.006%

    No Known Activations