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

    Neuronpedia

    INDEX
    Explanations

    programming tutorials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     初
    -0.07
     warranted
    -0.06
    Henry
    -0.06
     Yorkshire
    -0.06
    toHaveBeenCalledWith
    -0.06
    ında
    -0.06
    ละ
    -0.06
    cape
    -0.06
    로부터
    -0.06
    داشت
    -0.06
    POSITIVE LOGITS
     page
    0.06
     foods
    0.06
     працівників
    0.06
     McL
    0.06
    .paused
    0.06
    .gradient
    0.06
     essentially
    0.06
    _engine
    0.06
    ativity
    0.06
    -blog
    0.06
    Act Density 0.048%

    No Known Activations