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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tubes
    -0.07
    title
    -0.06
     těchto
    -0.06
    adients
    -0.06
     garant
    -0.05
    FilterWhere
    -0.05
    :CGRectMake
    -0.05
     osob
    -0.05
    介绍
    -0.05
     нег
    -0.05
    POSITIVE LOGITS
    rated
    0.07
     vyk
    0.07
    ฏ
    0.06
    	EIF
    0.06
     weaken
    0.06
    ICollectionView
    0.06
    ARR
    0.06
    \e
    0.06
     solitude
    0.06
     Searching
    0.06
    Act Density 0.017%

    No Known Activations