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

    Neuronpedia

    INDEX
    Explanations

    book snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кажет
    -0.07
    ично
    -0.07
    vt
    -0.07
    казывает
    -0.07
    となって
    -0.07
     sommes
    -0.07
    (tex
    -0.06
    itness
    -0.06
    今天我们
    -0.06
    竞价
    -0.06
    POSITIVE LOGITS
    ᴎ
    0.07
    Interval
    0.07
    .crypto
    0.06
    .display
    0.06
    Created
    0.06
    CEPTION
    0.06
     sliders
    0.06
    时机
    0.06
    โอ
    0.06
     boots
    0.06
    Act Density 0.018%

    No Known Activations