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

    Neuronpedia

    INDEX
    Explanations

    2 and 3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -\
    -0.07
     fines
    -0.07
     wy
    -0.07
    oday
    -0.06
    ować
    -0.06
     Mil
    -0.06
     vlas
    -0.06
     Paulo
    -0.06
    chemas
    -0.06
     detects
    -0.06
    POSITIVE LOGITS
    intValue
    0.07
    Reusable
    0.07
    aved
    0.06
    ODULE
    0.06
    _Call
    0.06
    InputGroup
    0.06
    _addr
    0.06
    esseract
    0.06
     特
    0.06
    бом
    0.06
    Act Density 0.002%

    No Known Activations