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

    Neuronpedia

    INDEX
    Explanations

    Locations, sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الغذ
    -0.09
     locator
    -0.08
     jaarlijks
    -0.08
     benchmarking
    -0.07
    ambira
    -0.07
     lokasi
    -0.07
     holog
    -0.07
     clothing
    -0.07
     шах
    -0.07
     jaarlijkse
    -0.07
    POSITIVE LOGITS
     molest
    0.08
    _chars
    0.08
    双方
    0.08
     incendi
    0.07
    _ang
    0.07
    standers
    0.07
     좀
    0.07
    稍
    0.07
     excell
    0.07
     carc
    0.07
    Act Density 0.047%

    No Known Activations