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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sequently
    -0.07
    cern
    -0.07
    RUN
    -0.07
    ünden
    -0.07
     действия
    -0.07
     cleanup
    -0.07
     مشاركة
    -0.06
    (util
    -0.06
     Than
    -0.06
    Probably
    -0.06
    POSITIVE LOGITS
    anos
    0.06
     전체
    0.06
    ("./
    0.06
     ◎
    0.06
    &page
    0.06
    <TResult
    0.06
     curly
    0.06
    }\"
    0.05
    Large
    0.05
     nei
    0.05
    Act Density 0.047%

    No Known Activations