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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -make
    -0.06
    静
    -0.06
    unned
    -0.06
     Ferdinand
    -0.06
    ῆς
    -0.06
    stří
    -0.06
     proxy
    -0.06
    timeofday
    -0.06
     Pedido
    -0.05
    XX
    -0.05
    POSITIVE LOGITS
     NORMAL
    0.07
     advertising
    0.07
    ORM
    0.07
    _UPDATE
    0.07
    ै।↵
    0.07
     Label
    0.06
     Parameter
    0.06
    kh
    0.06
    ORG
    0.06
     Bring
    0.06
    Act Density 0.003%

    No Known Activations