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

    Neuronpedia

    INDEX
    Explanations

    Living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =value
    -0.07
    quares
    -0.07
     وذلك
    -0.07
    _NAME
    -0.07
     устра
    -0.07
    ypse
    -0.07
    ازي
    -0.06
    DCF
    -0.06
    inions
    -0.06
     NAMES
    -0.06
    POSITIVE LOGITS
     �
    0.06
     disputed
    0.06
     purchasing
    0.06
     chiropr
    0.06
    .Font
    0.06
    speech
    0.06
     deceived
    0.06
     setShow
    0.06
     Podcast
    0.06
     ラ
    0.06
    Act Density 0.002%

    No Known Activations