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

    Neuronpedia

    INDEX
    Explanations

    Code blocks/loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متخصص
    -0.08
     documentaries
    -0.08
    etzt
    -0.07
     spezialisiert
    -0.07
     convolution
    -0.07
     подойдет
    -0.07
     Steiner
    -0.07
     specializes
    -0.07
    ({_
    -0.07
     dịch
    -0.07
    POSITIVE LOGITS
    Inside
    0.11
     эч
    0.10
    _inside
    0.10
     Inside
    0.10
    inside
    0.10
     اندر
    0.10
     inside
    0.10
    내용
    0.10
     actions
    0.09
     अंदर
    0.09
    Act Density 0.012%

    No Known Activations