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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accustomed
    -0.07
     उत
    -0.07
     हल
    -0.06
     ув
    -0.06
     TORT
    -0.06
    inci
    -0.06
     light
    -0.06
    ustralian
    -0.06
    _ZERO
    -0.06
     Former
    -0.06
    POSITIVE LOGITS
     Seit
    0.07
    libs
    0.07
     elems
    0.06
     asyncio
    0.06
     негатив
    0.06
     scary
    0.06
    střed
    0.06
     authService
    0.06
    形成
    0.06
    िच
    0.06
    Act Density 0.179%

    No Known Activations