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

    Neuronpedia

    INDEX
    Explanations

    self-improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sie
    -0.08
     social
    -0.07
    topics
    -0.07
    -abortion
    -0.07
    international
    -0.07
    already
    -0.06
    Federal
    -0.06
     seri
    -0.06
     Arabian
    -0.06
     Parent
    -0.06
    POSITIVE LOGITS
    řím
    0.07
    	Duel
    0.07
     oltre
    0.06
     éc
    0.06
     Zhu
    0.06
    .gridx
    0.06
    ��
    0.06
     مارس
    0.06
    	RTCK
    0.06
    ινη
    0.06
    Act Density 0.077%

    No Known Activations