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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lb
    -0.07
    -0.07
    	RE
    -0.06
    	answer
    -0.06
    스크
    -0.06
    006
    -0.06
     Ка
    -0.06
    ۱۲
    -0.06
    /theme
    -0.06
    straints
    -0.06
    POSITIVE LOGITS
     slova
    0.07
    ugh
    0.06
    .sigmoid
    0.06
     должен
    0.06
     anh
    0.06
    ữa
    0.06
    ARR
    0.06
    zahl
    0.06
     UserInfo
    0.06
     efficacy
    0.06
    Act Density 0.012%

    No Known Activations