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

    Neuronpedia

    INDEX
    Explanations

    stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Goth
    -0.08
    gth
    -0.07
    ��
    -0.07
    mc
    -0.07
    	self
    -0.06
    edl
    -0.06
    ρεια
    -0.06
     roles
    -0.06
     đường
    -0.06
     Democrats
    -0.06
    POSITIVE LOGITS
     Tik
    0.06
     sprink
    0.06
    ськ
    0.06
    をつ
    0.06
    ++++++++
    0.06
     karşı
    0.06
    溪
    0.06
    	static
    0.06
    (cmp
    0.06
    ैं,
    0.06
    Act Density 0.001%

    No Known Activations