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
    rien
    -0.07
    ạc
    -0.06
    -0.06
    uset
    -0.06
    oon
    -0.06
     looming
    -0.06
    ser
    -0.06
    eed
    -0.06
    ęki
    -0.06
     evils
    -0.06
    POSITIVE LOGITS
     sincerely
    0.07
     Д
    0.07
    ,"
    0.06
     famous
    0.06
    LOB
    0.06
    _standard
    0.06
    ,’
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
    /auth
    0.06
     contempl
    0.06
    Act Density 0.002%
    No Known Activations