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

    Neuronpedia

    INDEX
    Explanations

    first person pronoun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seven
    -0.07
     trav
    -0.07
    _qual
    -0.07
    Ve
    -0.06
     nose
    -0.06
    DEX
    -0.06
    Icon
    -0.06
    Slave
    -0.06
    .A
    -0.06
    .sc
    -0.06
    POSITIVE LOGITS
    -ng
    0.06
    :Get
    0.06
    -app
    0.06
     laptops
    0.06
    啊
    0.06
     nêu
    0.06
     návrh
    0.06
    ório
    0.06
     công
    0.06
     mužů
    0.06
    Act Density 0.099%

    No Known Activations