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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVA
    0.49
    HAL
    0.41
    MCA
    0.40
     inilah
    0.38
    ুধ
    0.38
     કોઈપણ
    0.38
    ﺹ
    0.38
     abgerufen
    0.37
    ION
    0.37
    ној
    0.37
    POSITIVE LOGITS
     the
    0.58
    lichkeiten
    0.49
     diğer
    0.45
     മറ്റു
    0.45
    the
    0.43
     otras
    0.43
     മറ്റ്
    0.43
    ных
    0.41
    蛲
    0.41
     නි
    0.41
    Act Density 0.000%

    No Known Activations