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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tah
    -0.07
    يلا
    -0.06
     sarà
    -0.06
    .Stat
    -0.06
    	scope
    -0.06
    �
    -0.06
     McKay
    -0.06
     Gad
    -0.06
     �
    -0.06
     Mayer
    -0.06
    POSITIVE LOGITS
     specialized
    0.08
    cion
    0.07
     specialised
    0.07
    .Inventory
    0.07
     savings
    0.06
     nej
    0.06
    .'));↵
    0.06
    (Collections
    0.06
     reported
    0.06
    DOWN
    0.06
    Act Density 0.075%

    No Known Activations