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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ázaro
    -1.38
    佼
    -1.33
     this
    -1.31
     encontramos
    -1.31
    に戻る
    -1.27
     that
    -1.27
     it
    -1.27
    吅
    -1.20
    ⃢
    -1.19
    _),
    -1.18
    POSITIVE LOGITS
     a
    1.45
    などを
    1.39
     two
    1.39
    が
    1.39
    卨
    1.38
    -
    1.31
    盉
    1.30
     وليس
    1.29
     chaîne
    1.25
    *
    1.21
    Act Density 0.173%

    No Known Activations