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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utter
    -0.07
     Kn
    -0.06
     sailors
    -0.06
    окрема
    -0.06
     kraje
    -0.06
     글
    -0.06
    _instructions
    -0.06
    都会
    -0.06
    arser
    -0.06
    Boston
    -0.06
    POSITIVE LOGITS
     hangi
    0.06
    asser
    0.06
     Joe
    0.06
     getApp
    0.06
     joe
    0.06
    กรรม
    0.06
     tz
    0.06
     Joey
    0.06
     Tibet
    0.06
     فيه
    0.06
    Act Density 0.001%

    No Known Activations