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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused338>
    0.28
    行き
    0.28
     labile
    0.28
    områ
    0.27
    espère
    0.27
    はある
    0.27
    ０
    0.27
     perverse
    0.26
    𐰚
    0.26
     outset
    0.26
    POSITIVE LOGITS
     the
    0.82
     The
    0.52
    the
    0.47
     teh
    0.44
     our
    0.44
     their
    0.41
    那个
    0.40
     a
    0.40
    The
    0.40
     an
    0.38
    Act Density 0.275%

    No Known Activations