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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negotiating
    -0.06
     MagicMock
    -0.06
    	editor
    -0.06
     sang
    -0.06
    oned
    -0.06
    _gain
    -0.06
    _profiles
    -0.06
     alanda
    -0.06
    Var
    -0.06
     Regards
    -0.06
    POSITIVE LOGITS
    如此
    0.07
    不是
    0.07
    ίου
    0.07
     tür
    0.06
     dừng
    0.06
     dạy
    0.06
     mereka
    0.06
     군
    0.06
     đai
    0.06
    jec
    0.06
    Act Density 0.227%

    No Known Activations