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

    Neuronpedia

    INDEX
    Explanations

    mind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Located
    -0.07
    getClient
    -0.07
    бав
    -0.07
    /orders
    -0.06
     sicher
    -0.06
     geçmiş
    -0.06
     hypocrisy
    -0.06
    Csv
    -0.06
    ;\↵
    -0.06
     خارجی
    -0.06
    POSITIVE LOGITS
    idd
    0.07
    OOD
    0.07
     troubles
    0.06
    ype
    0.06
    ­n
    0.06
     indifference
    0.06
    405
    0.06
     involves
    0.06
    431
    0.06
     evangel
    0.06
    Act Density 0.002%

    No Known Activations