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

    Neuronpedia

    INDEX
    Explanations

    say "service"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    иться
    -0.07
    -analytics
    -0.07
     title
    -0.06
    oleans
    -0.06
    memory
    -0.06
    	app
    -0.06
     */
↵
    -0.06
    gres
    -0.06
    Exclusive
    -0.06
    测试
    -0.06
    POSITIVE LOGITS
     xPos
    0.07
    ″
    0.07
     amb
    0.06
     đi
    0.06
     гум
    0.06
     overly
    0.06
     htons
    0.06
     wt
    0.06
    bindParam
    0.06
    _tF
    0.06
    Act Density 0.034%

    No Known Activations