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
     sincerity
    -0.07
    Person
    -0.06
    -0.06
    คอม
    -0.06
    _metrics
    -0.06
    -es
    -0.06
     brid
    -0.06
    (tm
    -0.06
     зменш
    -0.06
     september
    -0.06
    POSITIVE LOGITS
    -yyyy
    0.07
     foreach
    0.07
     AppBar
    0.07
    -------------↵
    0.07
     ediyor
    0.07
     replied
    0.06
    }_${
    0.06
    %">
    0.06
    olumes
    0.06
     Portrait
    0.06
    Act Density 0.007%

    No Known Activations