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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atta
    -0.07
     Yük
    -0.07
    endir
    -0.07
    ادي
    -0.06
     adjacent
    -0.06
    pty
    -0.06
    _Enc
    -0.06
     chap
    -0.06
     stří
    -0.06
    _sn
    -0.06
    POSITIVE LOGITS
    _updates
    0.07
     засобів
    0.07
    อย
    0.07
    нош
    0.06
    اقتص
    0.06
     boil
    0.06
    शन
    0.06
    BAD
    0.06
    	LEFT
    0.06
     Animal
    0.06
    Act Density 0.002%

    No Known Activations