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

    Neuronpedia

    INDEX
    Explanations

    Java packages and classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Submission
    -0.07
     assigned
    -0.07
    mainwindow
    -0.07
     previews
    -0.06
     subscribe
    -0.06
     saline
    -0.06
     tudo
    -0.06
    [word
    -0.06
    -buffer
    -0.06
     RAW
    -0.06
    POSITIVE LOGITS
    Τ
    0.08
    悴
    0.07
    abling
    0.07
    ف
    0.07
    HEADER
    0.07
     Litecoin
    0.07
    𝐟
    0.07
    实现
    0.07
    🌴
    0.07
    ģ
    0.07
    Act Density 0.002%

    No Known Activations