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

    Neuronpedia

    INDEX
    Explanations

    ships journeys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alchemy
    -0.07
    核酸
    -0.07
    [test
    -0.07
    TYPE
    -0.06
    为首的
    -0.06
    陳
    -0.06
     работник
    -0.06
     identifies
    -0.06
    Which
    -0.06
     development
    -0.06
    POSITIVE LOGITS
    >NN
    0.08
    僇
    0.07
     nipple
    0.07
     motivation
    0.07
    _dense
    0.07
    dream
    0.07
     Haven
    0.07
     radiator
    0.07
     TJ
    0.07
    لوم
    0.07
    Act Density 0.032%

    No Known Activations