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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	want
    -0.07
     Sav
    -0.06
    	x
    -0.06
    呈
    -0.06
    为什么
    -0.06
     raz
    -0.06
    徽
    -0.06
     тяжел
    -0.06
    avoid
    -0.06
    :|
    -0.06
    POSITIVE LOGITS
     znění
    0.07
    edm
    0.07
     جامعه
    0.06
    CastException
    0.06
     Enums
    0.06
    _inds
    0.06
    IFIC
    0.06
    _doc
    0.06
    (schema
    0.06
    ORG
    0.06
    Act Density 0.004%

    No Known Activations