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
     nonce
    -0.07
     facets
    -0.07
     Cure
    -0.06
     SSC
    -0.06
     Mezi
    -0.06
    cron
    -0.06
    Replacing
    -0.06
     엔
    -0.06
    indeki
    -0.06
    .lang
    -0.06
    POSITIVE LOGITS
     правильно
    0.07
     학생
    0.07
     saat
    0.07
    vous
    0.07
    iplina
    0.06
     крок
    0.06
    celed
    0.06
    .ViewModel
    0.06
    PyObject
    0.06
    Packet
    0.06
    Act Density 0.003%

    No Known Activations