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

    Neuronpedia

    INDEX
    Explanations

    ' or "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺎ
    0.89
     grieving
    0.86
    ﻤ
    0.84
    ﻘ
    0.83
     yaşanan
    0.80
     inadvertently
    0.79
     Bhagavato
    0.77
     этот
    0.77
    ﻦ
    0.77
     책
    0.76
    POSITIVE LOGITS
    ҷ
    0.69
    introspection
    0.68
    ለያዩ
    0.65
    互相
    0.64
    វា
    0.59
    初心者
    0.59
    ্লীল
    0.58
    Ἄ
    0.58
     nutshell
    0.57
    薫
    0.57
    Act Density 0.283%

    No Known Activations