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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their associated phrases indicating methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    means or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relatifs
    -0.41
    蘊
    -0.40
     fédé
    -0.40
    GEBURTS
    -0.39
     canst
    -0.39
    也許
    -0.39
     Besoin
    -0.39
    軀
    -0.39
    :✨
    -0.39
     perfons
    -0.39
    POSITIVE LOGITS
    WireFormatLite
    0.52
     Through
    0.51
    Through
    0.51
     through
    0.51
     Walkover
    0.49
     通过
    0.48
     yolu
    0.48
    inSlope
    0.47
     THROUGH
    0.47
     Administrativna
    0.46
    Act Density 0.298%

    No Known Activations