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
    uddled
    -0.06
     Το
    -0.06
     Bytes
    -0.06
     R
    -0.06
     Fil
    -0.06
     вироб
    -0.06
    	A
    -0.05
     hr
    -0.05
     zákaz
    -0.05
     standings
    -0.05
    POSITIVE LOGITS
    _of
    0.06
    처럼
    0.06
     �
    0.06
     civilians
    0.06
    let
    0.06
    .look
    0.06
    CEF
    0.06
     nanny
    0.06
    _geom
    0.06
     devam
    0.06
    Act Density 0.013%

    No Known Activations