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

    Neuronpedia

    INDEX
    Explanations

    bugs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DETAIL
    -0.08
     nghị
    -0.06
    .pop
    -0.06
     younger
    -0.06
     ulož
    -0.06
     foil
    -0.06
     anderen
    -0.06
                    
    -0.06
     depois
    -0.06
    120
    -0.06
    POSITIVE LOGITS
     flea
    0.09
    γραφ
    0.07
    setUp
    0.06
    ToString
    0.06
    Erot
    0.06
    ALER
    0.06
     Board
    0.06
     Mao
    0.06
     Вар
    0.06
    ありが
    0.06
    Act Density 0.017%

    No Known Activations