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
     furnace
    -0.07
     Cult
    -0.06
     MID
    -0.06
    径
    -0.06
    vari
    -0.06
     trunk
    -0.06
     SPI
    -0.06
    �
    -0.06
    بینی
    -0.06
     brewers
    -0.06
    POSITIVE LOGITS
    /opt
    0.09
     Paige
    0.08
    ·
    0.07
    .instances
    0.06
    ?),
    0.06
    ourney
    0.06
    _flg
    0.06
     naken
    0.06
    myModal
    0.06
    !),
    0.06
    Act Density 0.035%

    No Known Activations