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

    Neuronpedia

    INDEX
    Explanations

    related prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    感じで
    -1.35
    で見る
    -1.27
    で使
    -1.16
    為に
    -1.16
    の為
    -1.16
    に入れて
    -1.15
    事で
    -1.14
     abbin
    -1.14
     cómodo
    -1.13
     légère
    -1.08
    POSITIVE LOGITS
     to
    2.73
     into
    1.78
     on
    1.63
     towards
    1.30
     against
    1.28
     in
    1.27
    への
    1.23
     with
    1.19
     other
    1.15
    には
    1.13
    Act Density 0.162%

    No Known Activations