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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åijĹ
    -0.33
     -$
    -0.31
    busters
    -0.27
    ç¼ĸ
    -0.26
    ÑĨов
    -0.26
    Disposed
    -0.25
    oho
    -0.24
    outh
    -0.24
    åºķ
    -0.23
    ãĥķãĥĪ
    -0.23
    POSITIVE LOGITS
    few
    0.29
    å°±è¿Ļæł·
    0.27
    è¿Ļæł·
    0.26
    è¿Ļæł·çļĦè¯Ŀ
    0.26
    виÑĤ
    0.26
    延
    0.26
    è¿Ļä¹Ī说
    0.26
     BaseService
    0.25
    UTION
    0.25
     =================================================
    0.25
    Act Density 0.070%

    No Known Activations