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

    Neuronpedia

    INDEX
    Explanations

    code and logic statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    评论
    -0.07
    �
    -0.07
    76
    -0.06
     Rex
    -0.06
    작
    -0.06
    ))/(
    -0.06
    Worker
    -0.06
    ictions
    -0.06
    inheritDoc
    -0.06
    }")
    -0.06
    POSITIVE LOGITS
     kuk
    0.07
    DMIN
    0.06
    шем
    0.06
    DownList
    0.06
     prepend
    0.06
     rejoice
    0.06
    .White
    0.06
    .close
    0.06
    dq
    0.06
    roi
    0.06
    Act Density 0.167%

    No Known Activations