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

    Neuronpedia

    INDEX
    Explanations

    lists of segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дви
    0.39
     सल
    0.38
    ኩል
    0.38
     behavi
    0.38
    ibor
    0.37
     Über
    0.37
     acquis
    0.36
    impresa
    0.36
    ῖς
    0.36
     héro
    0.36
    POSITIVE LOGITS
    ందన్నారు
    0.41
    委员会
    0.40
    حم
    0.39
    listOf
    0.38
    鸡蛋
    0.36
     dichloromethane
    0.36
     TOC
    0.36
    តុ
    0.36
     methanol
    0.35
    lipstick
    0.35
    Act Density 0.000%

    No Known Activations