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

    Neuronpedia

    INDEX
    Explanations

    expressing personal feelings/opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sabbath
    -0.07
     名
    -0.06
     tournament
    -0.06
     methodName
    -0.06
     paras
    -0.06
    samp
    -0.06
    -0.06
     assertNull
    -0.06
    spam
    -0.06
     speaks
    -0.06
    POSITIVE LOGITS
     "))↵
    0.08
    /(?
    0.06
    성
    0.06
     weighed
    0.06
     Eins
    0.06
    )).↵
    0.06
    %',↵
    0.06
    ousands
    0.06
    під
    0.06
    }">↵
    0.06
    Act Density 0.096%

    No Known Activations