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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    API
    0.33
     Tiere
    0.32
    +
    0.32
    Κ
    0.29
     করিলে
    0.28
    5
    0.27
     Feuilles
    0.27
    IF
    0.27
    0
    0.27
    mRNA
    0.26
    POSITIVE LOGITS
     the
    0.66
     each
    0.45
     teh
    0.44
     your
    0.44
     our
    0.41
     cyberspace
    0.41
     their
    0.39
     both
    0.39
     an
    0.37
     every
    0.37
    Act Density 0.523%

    No Known Activations