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

    Neuronpedia

    INDEX
    Explanations

    Disagreement/Rebuttal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _record
    -0.08
     motivation
    -0.06
     بنی
    -0.06
    Fallback
    -0.06
    raised
    -0.06
    record
    -0.06
    ่ต
    -0.06
    	us
    -0.06
    _primary
    -0.06
    setFont
    -0.06
    POSITIVE LOGITS
     servicing
    0.07
     Αρ
    0.06
     examines
    0.06
    集团
    0.06
     encrypt
    0.06
     Một
    0.06
     Elev
    0.06
     UTC
    0.06
     Swords
    0.06
     Lieutenant
    0.06
    Act Density 0.145%

    No Known Activations