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

    Neuronpedia

    INDEX
    Explanations

    first followed by common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.70
    년
    1.47
    AZIONE
    1.44
    个
    1.38
    년에
    1.34
    冫
    1.34
     ﺍﻟ
    1.33
    ளில்
    1.32
    浻
    1.32
    我
    1.31
    POSITIVE LOGITS
     responders
    1.41
     baseman
    1.29
     tranche
    1.16
     responder
    1.14
    ارة
    1.13
     pollution
    1.08
     ventilation
    1.07
     والث
    1.07
    iary
    1.06
     tiên
    1.05
    Act Density 0.048%

    No Known Activations