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

    Neuronpedia

    INDEX
    Explanations

    the or in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    合い
    -0.07
    ࡑ
    -0.07
     rugged
    -0.07
     wohl
    -0.07
     cậu
    -0.07
    רה
    -0.06
    投入
    -0.06
    ัย
    -0.06
    põ
    -0.06
    osa
    -0.06
    POSITIVE LOGITS
    /accounts
    0.08
    _this
    0.07
    _hs
    0.07
    /Foundation
    0.07
    ordinal
    0.07
     Ord
    0.07
    科学研究
    0.07
    .timestamp
    0.07
    .future
    0.07
     enthus
    0.07
    Act Density 0.004%

    No Known Activations