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

    Neuronpedia

    INDEX
    Explanations

    URL shorteners and tweets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rides
    -0.07
     nikdo
    -0.07
     memberId
    -0.06
    頂
    -0.06
     OBS
    -0.06
     bash
    -0.06
    andatory
    -0.06
     cent
    -0.06
     unr
    -0.06
    ACES
    -0.06
    POSITIVE LOGITS
    (trigger
    0.07
    {*
    0.07
     những
    0.07
     crisp
    0.06
     đặc
    0.06
    所有
    0.06
     ایجاد
    0.06
     Xi
    0.06
    ointment
    0.06
     tomu
    0.06
    Act Density 0.001%

    No Known Activations