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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Opened
    -0.07
    _SCL
    -0.07
    ủy
    -0.07
    handler
    -0.06
    (GUI
    -0.06
    alem
    -0.06
     Voor
    -0.06
    ěj
    -0.06
    ynı
    -0.06
    ैय
    -0.06
    POSITIVE LOGITS
    AGE
    0.07
    oth
    0.07
     educational
    0.07
     civil
    0.07
     the
    0.06
     newArray
    0.06
     flipping
    0.06
    age
    0.06
     hereby
    0.06
    ',
↵
    0.06
    Act Density 0.311%

    No Known Activations