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

    Neuronpedia

    INDEX
    Explanations

    data extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حالی
    -0.07
    ishments
    -0.06
     licenses
    -0.06
     تغییر
    -0.06
    ifestyle
    -0.06
    Berlin
    -0.06
    Severity
    -0.06
     엘
    -0.06
     Princeton
    -0.06
     horrified
    -0.06
    POSITIVE LOGITS
     движ
    0.07
     punto
    0.07
    到底
    0.06
    .mozilla
    0.06
    gly
    0.06
     누구
    0.06
    }`,
    0.06
    準
    0.06
     MLA
    0.06
    :none
    0.06
    Act Density 0.058%

    No Known Activations