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

    Neuronpedia

    INDEX
    Explanations

    colon punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depicted
    -0.08
     stronger
    -0.07
     unify
    -0.07
    增强
    -0.07
     ترغب
    -0.07
     depict
    -0.07
    .Memory
    -0.07
    创
    -0.07
    .Expect
    -0.07
    押
    -0.07
    POSITIVE LOGITS
    _QUERY
    0.09
    	Query
    0.08
     Nathan
    0.08
     interrogation
    0.08
     Siv
    0.08
     interrog
    0.08
     verplicht
    0.08
     moreover
    0.08
     Unt
    0.08
     queried
    0.08
    Act Density 0.001%

    No Known Activations