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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quat
    -0.07
    プ
    -0.06
    Priority
    -0.06
    _OPT
    -0.06
    rectangle
    -0.06
    findOne
    -0.06
     loyal
    -0.06
     immature
    -0.06
     Mockito
    -0.06
     Lowest
    -0.06
    POSITIVE LOGITS
     ايران
    0.08
     expectedResult
    0.06
     verdi
    0.06
    _SEL
    0.06
    倫
    0.06
    .dy
    0.06
    uce
    0.06
    _YEAR
    0.06
    illy
    0.06
    rå
    0.06
    Act Density 0.020%

    No Known Activations