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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ighbour
    -0.08
    _counter
    -0.08
    incre
    -0.08
    Professor
    -0.07
     protested
    -0.07
     З
    -0.07
     지난
    -0.07
    .Once
    -0.07
    	Vk
    -0.07
     toen
    -0.07
    POSITIVE LOGITS
    蒴
    0.07
    mia
    0.07
    دس
    0.07
    븐
    0.07
    빽
    0.07
    玛丽
    0.07
    坏事
    0.07
    쾰
    0.07
    Ӕ
    0.06
     cockpit
    0.06
    Act Density 0.004%

    No Known Activations