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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amentos
    -0.07
    Prototype
    -0.07
    hole
    -0.07
    ideas
    -0.07
    常态化
    -0.07
    🦋
    -0.07
    Ģ
    -0.07
    腋
    -0.06
    houette
    -0.06
    accel
    -0.06
    POSITIVE LOGITS
    樨
    0.08
    :error
    0.07
     Preferred
    0.07
     nat
    0.07
     nhấn
    0.06
    낌
    0.06
    This
    0.06
    otine
    0.06
    咡
    0.06
    _foot
    0.06
    Act Density 0.218%

    No Known Activations