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

    Neuronpedia

    INDEX
    Explanations

    language codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    輪
    -0.07
     sop
    -0.07
    pest
    -0.07
     Nora
    -0.06
     Papers
    -0.06
    IBC
    -0.06
     Cards
    -0.06
    IBUTES
    -0.06
    ificado
    -0.06
     Skipping
    -0.06
    POSITIVE LOGITS
    .selenium
    0.07
    edii
    0.07
     miệng
    0.06
    توان
    0.06
     LatLng
    0.06
    "><?
    0.06
    	speed
    0.06
    �试
    0.06
     mắc
    0.06
    询
    0.06
    Act Density 0.004%

    No Known Activations