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

    Neuronpedia

    INDEX
    Explanations

    security vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zahlung
    -0.07
    казать
    -0.07
    buch
    -0.07
    arzt
    -0.07
    认为
    -0.07
    onet
    -0.07
     Fiesta
    -0.07
     Unterhaltung
    -0.07
    ינג
    -0.07
     فوق
    -0.07
    POSITIVE LOGITS
     víctimas
    0.09
    _CPP
    0.08
    Clientes
    0.08
    .Concurrent
    0.08
     Clientes
    0.08
     enctype
    0.07
     trouxe
    0.07
     JFile
    0.07
     chaidh
    0.07
     nase
    0.07
    Act Density 0.000%

    No Known Activations