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

    Neuronpedia

    INDEX
    Explanations

    raise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     López
    -0.07
    挣扎
    -0.07
     vulnerability
    -0.07
     BMC
    -0.07
     Connectivity
    -0.06
     ATP
    -0.06
    undi
    -0.06
    Polygon
    -0.06
     Buffy
    -0.06
    مكونات
    -0.06
    POSITIVE LOGITS
     raise
    0.10
    ഹ
    0.07
    iesta
    0.07
    rien
    0.07
    	raise
    0.07
    (al
    0.07
     praised
    0.07
     الحقوق
    0.07
     raising
    0.07
    raise
    0.07
    Act Density 0.010%

    No Known Activations