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

    Neuronpedia

    INDEX
    Explanations

    percent symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mass
    -0.07
     робіт
    -0.07
    ”?
    -0.07
    арт
    -0.06
     thêm
    -0.06
    learning
    -0.06
     region
    -0.06
     sea
    -0.06
     mobility
    -0.06
     fans
    -0.06
    POSITIVE LOGITS
    Script
    0.07
     หน
    0.06
     pense
    0.06
    DialogTitle
    0.06
    /groups
    0.06
    방
    0.06
     충
    0.06
     Contents
    0.06
    	Dictionary
    0.06
     nonexistent
    0.06
    Act Density 0.013%

    No Known Activations