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

    Neuronpedia

    INDEX
    Explanations

    being utterly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undis
    0.41
     hiding
    0.39
     मल
    0.38
    luğ
    0.36
    ServletContext
    0.35
    জুর
    0.34
    Regardless
    0.34
    竹
    0.34
    ardless
    0.34
     கூடு
    0.34
    POSITIVE LOGITS
     rectify
    0.41
     rectified
    0.40
     Dorothy
    0.39
     دوسرا
    0.38
     Consume
    0.38
     consumo
    0.38
     Derive
    0.37
     Tav
    0.37
     utensils
    0.36
     Consumption
    0.36
    Act Density 0.003%

    No Known Activations