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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .__
    -0.07
    verified
    -0.07
     Unicode
    -0.07
     navigator
    -0.07
    ibur
    -0.07
    cta
    -0.06
     interior
    -0.06
     Wells
    -0.06
    Morning
    -0.06
     paying
    -0.06
    POSITIVE LOGITS
    -valu
    0.06
     anecd
    0.06
    قلال
    0.06
    ियत
    0.06
     Researchers
    0.06
    ,length
    0.06
     Levels
    0.05
    ocusing
    0.05
    گونه
    0.05
    OND
    0.05
    Act Density 0.087%

    No Known Activations