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

    Neuronpedia

    INDEX
    Explanations

    NASCAR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мн
    -0.07
     vin
    -0.07
     humidity
    -0.07
     publi
    -0.06
    Woman
    -0.06
     attention
    -0.06
     обращ
    -0.06
     knowledge
    -0.06
     testcase
    -0.06
     трав
    -0.06
    POSITIVE LOGITS
    ạ
    0.07
     το
    0.06
     гер
    0.06
    quer
    0.06
    "]){↵
    0.06
    ]){
↵
    0.06
    adium
    0.06
     inse
    0.06
    ...");
↵
    0.06
     Europ
    0.06
    Act Density 0.017%

    No Known Activations