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

    Neuronpedia

    INDEX
    Explanations

    PC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     根
    -0.08
     Bangladesh
    -0.07
    _messages
    -0.07
    ん
    -0.07
    -google
    -0.07
    enes
    -0.07
     CY
    -0.07
     reass
    -0.07
     Opp
    -0.07
     flat
    -0.07
    POSITIVE LOGITS
     후보
    0.07
     Avrupa
    0.06
    اصيل
    0.06
    istique
    0.06
     проведення
    0.06
    ++
    0.06
    592
    0.06
     sele
    0.06
    _fe
    0.05
    >Loading
    0.05
    Act Density 0.035%

    No Known Activations