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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or contexts of movement and action

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

    Prepositions like "through" and "under"

    np_acts-logits-general · gemini-2.0-flash

    through, under, against, during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vermelhas
    -0.84
     brancas
    -0.80
     noastre
    -0.80
     nostru
    -0.76
     deoarece
    -0.74
     âgées
    -0.73
     suivantes
    -0.72
     înainte
    -0.71
     noastră
    -0.70
     vectorielles
    -0.69
    POSITIVE LOGITS
     the
    1.55
     its
    1.11
     a
    1.11
     both
    1.08
     their
    1.06
     an
    1.03
     either
    1.01
     whom
    0.99
     those
    0.98
     these
    0.97
    Act Density 0.555%

    No Known Activations