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

    Neuronpedia

    INDEX
    Explanations

    start followed by separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    之路
    0.42
     started
    0.40
     constructing
    0.39
    表达
    0.39
     negotiations
    0.38
    山本
    0.38
    剿
    0.38
    ৮
    0.38
    بيع
    0.38
     lys
    0.37
    POSITIVE LOGITS
    liners
    0.46
    tls
    0.44
    ierende
    0.42
    end
    0.42
    आती
    0.42
    swith
    0.40
    wood
    0.40
    oe
    0.39
    oble
    0.39
    ting
    0.38
    Act Density 0.022%

    No Known Activations