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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीव
    -0.07
    .LA
    -0.07
    ending
    -0.07
    .ph
    -0.07
     Correspond
    -0.06
    alist
    -0.06
     dis
    -0.06
     otro
    -0.06
    casting
    -0.06
    ества
    -0.06
    POSITIVE LOGITS
    Your
    0.06
    USART
    0.06
    'RE
    0.06
    ंटर
    0.06
     أج
    0.06
     Britain
    0.06
     百度收录
    0.06
     dern
    0.06
    (serv
    0.06
     můžete
    0.06
    Act Density 0.028%

    No Known Activations