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

    Neuronpedia

    INDEX
    Explanations

    depending on condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সঞ্জ
    0.52
     Padding
    0.48
     प्रोट
    0.48
     गह
    0.48
    дэ
    0.47
     подготов
    0.47
     дополнительных
    0.47
     comenzamos
    0.47
     Awake
    0.46
     下载
    0.45
    POSITIVE LOGITS
    dings
    0.47
    ]->
    0.43
    ownership
    0.43
     sight
    0.41
    त्कार
    0.41
    bara
    0.40
    fighters
    0.40
    rocities
    0.39
     purview
    0.38
    รรม
    0.38
    Act Density 0.006%

    No Known Activations