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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bekan
    -0.07
     협
    -0.07
    Begin
    -0.06
    PRICE
    -0.06
     Coke
    -0.06
     grievances
    -0.06
     광
    -0.06
     errone
    -0.06
     Але
    -0.06
    _PIX
    -0.06
    POSITIVE LOGITS
    <p
    0.07
    _<
    0.06
     Seminar
    0.06
    <v
    0.06
    )(↵
    0.06
     skepticism
    0.06
     currentPlayer
    0.06
    %X
    0.06
     Iterator
    0.06
    (&_
    0.06
    Act Density 0.011%

    No Known Activations