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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Matth
    -0.06
    /me
    -0.06
     Lips
    -0.06
     brill
    -0.06
     mess
    -0.06
    .quality
    -0.06
    区域
    -0.06
     Fou
    -0.06
    ındaki
    -0.06
    exas
    -0.06
    POSITIVE LOGITS
    what
    0.06
    κυ
    0.06
    	output
    0.06
     objc
    0.06
    _As
    0.06
     DirectX
    0.06
    Người
    0.06
    ROUGH
    0.06
    _DO
    0.06
    -handle
    0.06
    Act Density 0.670%

    No Known Activations