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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LIN
    -0.07
    로
    -0.06
     KeyError
    -0.06
     eq
    -0.06
     bent
    -0.06
     neuen
    -0.06
    _crit
    -0.06
     credits
    -0.06
     REPLACE
    -0.06
     to
    -0.06
    POSITIVE LOGITS
     Seoul
    0.06
     respons
    0.06
    _reporting
    0.06
     přih
    0.06
    Params
    0.06
     مصر
    0.06
     склад
    0.06
     �
    0.06
     �
    0.06
     accru
    0.06
    Act Density 0.056%

    No Known Activations