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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ัฒ
    -0.07
     Bus
    -0.07
    络
    -0.07
     allegiance
    -0.07
     of
    -0.06
    '/>↵
    -0.06
     against
    -0.06
     de
    -0.06
    述
    -0.06
    见
    -0.06
    POSITIVE LOGITS
    objectManager
    0.06
     berk
    0.06
    Australia
    0.06
    	ss
    0.06
    izacion
    0.06
     ATTR
    0.06
    心
    0.06
    Spot
    0.06
    Starting
    0.05
    .MenuItem
    0.05
    Act Density 0.027%

    No Known Activations