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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ຢູ່ໃນ
    0.32
    gdock
    0.32
    戏剧
    0.31
    邰
    0.31
    SrvGroup
    0.31
    举办
    0.31
    ังหวัด
    0.31
    营造
    0.31
    变革
    0.31
    𒊩
    0.31
    POSITIVE LOGITS
    0.45
     =
    0.42
    ↵
    0.38
    0
    0.38
     $
    0.37
     the
    0.37
    5
    0.35
    6
    0.34
    8
    0.33
    3
    0.33
    Act Density 0.326%

    No Known Activations