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

    Neuronpedia

    INDEX
    Explanations

    pd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Executive
    -0.08
    Hook
    -0.07
     stere
    -0.07
     Gui
    -0.07
     Eng
    -0.07
    .inner
    -0.07
    ,E
    -0.06
     Stereo
    -0.06
    ольш
    -0.06
     trụ
    -0.06
    POSITIVE LOGITS
    ώρα
    0.07
     scratching
    0.06
    ове
    0.06
     repent
    0.06
    知道
    0.06
     Kind
    0.06
    yg
    0.06
    nette
    0.06
    	sd
    0.06
    ANCEL
    0.06
    Act Density 0.003%

    No Known Activations