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

    Neuronpedia

    INDEX
    Explanations

    chemical/material usage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xxx
    -0.06
     Elegant
    -0.06
     jean
    -0.06
     treat
    -0.06
     Ult
    -0.06
    ced
    -0.06
     exiting
    -0.06
    SUR
    -0.06
    这样
    -0.06
     lobby
    -0.06
    POSITIVE LOGITS
    .Autowired
    0.06
    ijd
    0.06
     Müslüman
    0.06
     ομάδα
    0.06
     yapar
    0.06
    .randn
    0.06
    Yii
    0.06
     PO
    0.06
     -*
    0.06
     огра
    0.06
    Act Density 0.056%

    No Known Activations