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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .deleted
    -0.07
    logy
    -0.07
    Eric
    -0.07
     správ
    -0.07
    دا
    -0.07
     تلفن
    -0.07
     pytest
    -0.07
     потрап
    -0.07
    .Detail
    -0.07
    jam
    -0.06
    POSITIVE LOGITS
    ційного
    0.06
     firstname
    0.06
    -unstyled
    0.06
    ADD
    0.06
     mad
    0.06
     전세
    0.06
    htt
    0.06
     depressive
    0.06
    emente
    0.06
    <Book
    0.06
    Act Density 0.017%

    No Known Activations