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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuller
    -0.07
    ih
    -0.07
     obtained
    -0.07
    _search
    -0.06
    Global
    -0.06
     obtaining
    -0.06
     obtain
    -0.06
     ###↵
    -0.06
    avored
    -0.06
    -sn
    -0.06
    POSITIVE LOGITS
    织
    0.07
    gatsby
    0.07
    ’nda
    0.07
     věci
    0.07
    ło
    0.06
     luggage
    0.06
    weets
    0.06
    DrawerToggle
    0.06
     fireEvent
    0.06
     USART
    0.06
    Act Density 0.022%

    No Known Activations