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

    Neuronpedia

    INDEX
    Explanations

    ){

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     /*↵
    -0.07
    ığı
    -0.07
    mx
    -0.06
    146
    -0.06
    šetř
    -0.06
    MISS
    -0.06
    Column
    -0.06
     paypal
    -0.06
    Mail
    -0.06
    Spy
    -0.06
    POSITIVE LOGITS
     leakage
    0.07
    оза
    0.06
     etiquette
    0.06
    คโน
    0.06
    aceut
    0.06
     Komment
    0.06
     CPPUNIT
    0.06
    DefaultCloseOperation
    0.06
     INFORMATION
    0.06
     Calcium
    0.06
    Act Density 0.001%

    No Known Activations