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

    Neuronpedia

    INDEX
    Explanations

    speaking commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tosc
    0.39
     list
    0.38
     Jot
    0.38
     X
    0.38
     pillars
    0.38
     Nessa
    0.37
     men
    0.37
    whis
    0.36
     pai
    0.36
     Yin
    0.36
    POSITIVE LOGITS
     الأمن
    0.41
     ശേഷ
    0.39
    ولوژی
    0.39
    ৪৪
    0.39
     forensics
    0.38
    SafeArea
    0.38
    ົບ
    0.37
     forensic
    0.37
    具体
    0.36
    咨询
    0.36
    Act Density 0.001%

    No Known Activations