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

    Neuronpedia

    INDEX
    Explanations

    improve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    附
    -0.07
     Aid
    -0.07
     чай
    -0.07
     vals
    -0.07
    	set
    -0.06
    former
    -0.06
    _df
    -0.06
    .thread
    -0.06
     rainfall
    -0.06
    pections
    -0.06
    POSITIVE LOGITS
    ۲۹
    0.07
    reste
    0.06
    ัฐ
    0.06
     знаю
    0.06
    VisualStyle
    0.06
    ÃO
    0.06
     стра
    0.06
     knull
    0.06
     muốn
    0.06
    الله
    0.06
    Act Density 0.024%

    No Known Activations