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

    Neuronpedia

    INDEX
    Explanations

    any have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biases
    -0.06
     rm
    -0.06
     aerial
    -0.06
    Timeout
    -0.06
     solicit
    -0.06
    合
    -0.06
    喊
    -0.06
     assez
    -0.06
    样的
    -0.06
     Imper
    -0.06
    POSITIVE LOGITS
    <button
    0.07
     نمود
    0.07
    dd
    0.07
     Essen
    0.07
     és
    0.07
    venue
    0.06
    iname
    0.06
     Option
    0.06
     освещ
    0.06
    izio
    0.06
    Act Density 0.018%

    No Known Activations