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

    Neuronpedia

    INDEX
    Explanations

    standard interface or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的一种
    0.42
     биологи
    0.40
    一种
    0.36
    生物
    0.36
     非
    0.36
     自然
    0.36
    认为是
    0.36
     જીવન
    0.36
     психи
    0.35
     ανθρώ
    0.35
    POSITIVE LOGITS
     comprehensive
    0.34
     and
    0.33
     beho
    0.31
     top
    0.31
     full
    0.30
     combo
    0.30
     big
    0.30
     D
    0.29
     arsenal
    0.29
     Team
    0.29
    Act Density 0.906%

    No Known Activations