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

    Neuronpedia

    INDEX
    Explanations

    hypothetical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Normalized
    -0.07
    .HORIZONTAL
    -0.06
     SUBJECT
    -0.06
    	Random
    -0.06
    -review
    -0.06
     batt
    -0.06
    870
    -0.06
    (models
    -0.06
     modeled
    -0.06
     предмет
    -0.06
    POSITIVE LOGITS
     would
    0.08
     snapchat
    0.07
    shop
    0.07
    forums
    0.07
    ıs
    0.07
    啪
    0.07
     의미
    0.06
    SHOP
    0.06
    :::/
    0.06
    would
    0.06
    Act Density 0.106%

    No Known Activations