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

    Neuronpedia

    INDEX
    Explanations

    Code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QP
    -0.07
     EDT
    -0.07
    IOException
    -0.07
     RESPONS
    -0.07
     écrit
    -0.07
     Salman
    -0.06
     sitios
    -0.06
     станд
    -0.06
     سبب
    -0.06
    ############
    -0.06
    POSITIVE LOGITS
     recreate
    0.07
     θ
    0.06
     применения
    0.06
     thí
    0.06
     Horn
    0.06
     ¬
    0.06
    conduct
    0.06
    Viewport
    0.06
    _med
    0.06
    ピ
    0.06
    Act Density 0.001%

    No Known Activations