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

    Neuronpedia

    INDEX
    Explanations

    gzip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (',')[
    -0.07
    /?
    -0.07
    .AppendLine
    -0.07
    🤑
    -0.07
    现实中
    -0.07
    💓
    -0.07
    undai
    -0.07
    眭
    -0.06
     Doctor
    -0.06
    没事
    -0.06
    POSITIVE LOGITS
    对他
    0.08
     gun
    0.07
     experiments
    0.07
     reim
    0.07
     gzip
    0.07
     история
    0.07
     crus
    0.07
     demolition
    0.07
    䓬
    0.07
    file
    0.07
    Act Density 0.001%

    No Known Activations