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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     español
    -0.07
     chore
    -0.06
     spanking
    -0.06
     standout
    -0.06
    =sc
    -0.06
     yêu
    -0.06
     isSelected
    -0.06
     Concrete
    -0.06
     university
    -0.06
     chops
    -0.06
    POSITIVE LOGITS
    /__
    0.07
     Sites
    0.06
    .ipv
    0.06
    報告
    0.06
    "]."
    0.06
    _cid
    0.06
    문제
    0.06
     uyum
    0.06
    -wsj
    0.06
    ГО
    0.06
    Act Density 0.390%

    No Known Activations