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

    Neuronpedia

    INDEX
    Explanations

    listing specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VOR
    0.46
    Fiscal
    0.45
    Maar
    0.45
     аўтаматы
    0.43
    ర్థిక
    0.43
    櫳
    0.43
     suất
    0.43
    ισμού
    0.42
    COLORS
    0.42
    经济
    0.41
    POSITIVE LOGITS
     hirs
    0.48
     png
    0.46
    pleasant
    0.44
     towards
    0.43
     ts
    0.43
     UI
    0.42
     ui
    0.42
     overlying
    0.42
     dict
    0.41
     impug
    0.41
    Act Density 0.011%

    No Known Activations