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

    Neuronpedia

    INDEX
    Explanations

    上

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zn
    -0.07
     QDom
    -0.07
     deutschland
    -0.07
    设施
    -0.07
     영국
    -0.06
     Jo
    -0.06
     Couldn
    -0.06
    taient
    -0.06
     Jest
    -0.06
    cnt
    -0.06
    POSITIVE LOGITS
    -sub
    0.07
    arshal
    0.07
     Browns
    0.07
    _lo
    0.07
     scripted
    0.06
    Anchor
    0.06
    aw
    0.06
    VERSION
    0.06
    IDDLE
    0.06
    ARSE
    0.06
    Act Density 0.011%

    No Known Activations