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

    Neuronpedia

    INDEX
    Explanations

    Code and definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PAD
    -0.07
     아무
    -0.06
    setCurrent
    -0.06
    /apps
    -0.06
    Ѭ
    -0.06
    جال
    -0.06
     proton
    -0.06
    쐐
    -0.06
     THEIR
    -0.06
    大庆
    -0.06
    POSITIVE LOGITS
     Blocking
    0.07
    	container
    0.07
    డ
    0.07
    (rec
    0.07
    毙
    0.06
    permit
    0.06
    (slot
    0.06
    oug
    0.06
    (li
    0.06
     Wick
    0.06
    Act Density 0.000%

    No Known Activations