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

    Neuronpedia

    INDEX
    Explanations

    the followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቱን
    0.31
     fares
    0.30
     egregious
    0.29
    ቹን
    0.28
     infraction
    0.27
    originals
    0.27
     warranted
    0.25
     phrasing
    0.25
     cited
    0.25
     infractions
    0.25
    POSITIVE LOGITS
     permukaan
    0.33
     Bedürfnisse
    0.31
     superfície
    0.30
     superficie
    0.29
     parede
    0.29
     Oberfläche
    0.28
     eixo
    0.28
     belakang
    0.28
     Scandinavia
    0.28
     aplikacji
    0.28
    Act Density 0.054%

    No Known Activations