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

    Neuronpedia

    INDEX
    Explanations

    overtime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    感情
    -0.07
    Letter
    -0.07
     preprocess
    -0.07
    lix
    -0.07
    Vi
    -0.06
    rir
    -0.06
    Jean
    -0.06
    Ok
    -0.06
     Blade
    -0.06
     metod
    -0.06
    POSITIVE LOGITS
    awner
    0.06
    "]];↵
    0.06
     overtime
    0.06
    .exist
    0.06
     miracle
    0.06
     nhiễ
    0.06
     Bison
    0.06
     typeName
    0.06
    vertime
    0.06
    ()]);↵
    0.06
    Act Density 0.001%

    No Known Activations