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

    Neuronpedia

    INDEX
    Explanations

    contextual prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इसमें
    0.65
    te
    0.65
    de
    0.65
    In
    0.64
    에
    0.63
    it
    0.58
    ك
    0.58
    et
    0.58
    and
    0.57
    It
    0.57
    POSITIVE LOGITS
     conjunction
    1.38
     accordance
    1.38
     terms
    1.27
     lieu
    1.20
     spite
    1.16
     addition
    1.10
     relation
    1.07
     rámci
    1.02
     order
    1.00
     regards
    0.97
    Act Density 0.551%

    No Known Activations