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

    Neuronpedia

    INDEX
    Explanations

    Express

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currentNode
    -0.07
    חם
    -0.07
     thẳng
    -0.07
    引っ
    -0.07
    ⍲
    -0.07
    짚
    -0.07
    돌
    -0.07
    ㉠
    -0.06
     Dav
    -0.06
    計算
    -0.06
    POSITIVE LOGITS
     способ
    0.08
    identified
    0.07
    лей
    0.07
     median
    0.07
    обесп
    0.07
    approved
    0.07
    итель
    0.07
    警
    0.07
    prefer
    0.07
    Increasing
    0.07
    Act Density 0.001%

    No Known Activations