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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blob
    -0.07
     exploding
    -0.07
    _trace
    -0.07
    Store
    -0.07
    (prob
    -0.06
    ashes
    -0.06
    250
    -0.06
     العربية
    -0.06
    -Shirt
    -0.06
     phiếu
    -0.06
    POSITIVE LOGITS
     masturbation
    0.06
     GestureDetector
    0.06
     các
    0.06
    .Iterator
    0.06
     kinds
    0.06
    	api
    0.06
    :`~
    0.06
     gli
    0.06
     Shared
    0.06
     {[%
    0.05
    Act Density 0.257%

    No Known Activations