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

    Neuronpedia

    INDEX
    Explanations

    Auctions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Studios
    -0.07
     mer
    -0.07
    ��
    -0.07
     Hudson
    -0.07
     Engineers
    -0.06
    _datas
    -0.06
    _Exception
    -0.06
    inson
    -0.06
    .bucket
    -0.06
     kali
    -0.06
    POSITIVE LOGITS
    	width
    0.07
    одав
    0.06
     hely
    0.06
    ubl
    0.06
    微笑
    0.06
     behaves
    0.06
     selv
    0.06
     пн
    0.06
     mücadel
    0.06
     güc
    0.06
    Act Density 0.035%

    No Known Activations