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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osopher
    -0.07
    _NOTICE
    -0.06
    &display
    -0.06
     up
    -0.06
    sworth
    -0.06
     Configure
    -0.06
     greet
    -0.06
    ึก
    -0.06
     Fatal
    -0.06
     timezone
    -0.06
    POSITIVE LOGITS
     nông
    0.06
    游戏
    0.06
     fragmented
    0.06
     qualitative
    0.06
    ởi
    0.06
     exemptions
    0.06
    nul
    0.06
    ogie
    0.06
     sexist
    0.06
    cript
    0.06
    Act Density 0.033%

    No Known Activations