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

    Neuronpedia

    INDEX
    Explanations

    accessing data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ву
    -0.07
    va
    -0.07
    sin
    -0.07
    _norm
    -0.07
     условия
    -0.06
    	LOGGER
    -0.06
    lius
    -0.06
    mess
    -0.06
     worldly
    -0.06
     chịu
    -0.06
    POSITIVE LOGITS
     origen
    0.07
    -android
    0.07
     detectives
    0.06
     detainees
    0.06
    动物
    0.06
    ЕТ
    0.06
    ORG
    0.06
     ██
    0.06
    charAt
    0.06
     мест
    0.06
    Act Density 0.002%

    No Known Activations