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

    Neuronpedia

    INDEX
    Explanations

    general descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quals
    -0.07
     Ethi
    -0.06
     reh
    -0.06
    되어
    -0.06
     pstmt
    -0.06
    奈
    -0.06
    521
    -0.06
    내
    -0.06
    銀
    -0.06
     painstaking
    -0.06
    POSITIVE LOGITS
    ộng
    0.06
    .ย
    0.06
    forEach
    0.06
    Eat
    0.06
     priorit
    0.06
    .atom
    0.06
     Civic
    0.05
    roz
    0.05
    #index
    0.05
    	Title
    0.05
    Act Density 0.102%

    No Known Activations