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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bmp
    -0.07
    AML
    -0.06
     Ivan
    -0.06
     Soldiers
    -0.06
    people
    -0.06
     admiration
    -0.06
    route
    -0.06
    control
    -0.06
     ihnen
    -0.06
    確認
    -0.06
    POSITIVE LOGITS
     ${(
    0.07
     ori
    0.07
     ArgumentException
    0.07
     unstable
    0.06
     radioButton
    0.06
     Annie
    0.06
    ابقات
    0.06
    uyển
    0.06
     sucked
    0.06
     बर
    0.06
    Act Density 0.007%

    No Known Activations