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

    Neuronpedia

    INDEX
    Explanations

    square brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fxml
    -0.08
    cient
    -0.08
    queda
    -0.08
    stander
    -0.08
    ~~
    -0.08
    ttps
    -0.08
    ۇپ
    -0.07
    apult
    -0.07
     Qu
    -0.07
     caffe
    -0.07
    POSITIVE LOGITS
     abb
    0.08
     irrespective
    0.08
     battery
    0.08
     stocked
    0.07
     напряж
    0.07
     ira
    0.07
     اسمبلی
    0.07
     Constructors
    0.07
    Manufacturer
    0.07
     रंग
    0.07
    Act Density 0.005%

    No Known Activations