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

    Neuronpedia

    INDEX
    Explanations

    instances of similarity or comparison between concepts or situations

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

    same or similar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     边框
    -0.40
    fordern
    -0.39
    rativo
    -0.39
     sceptre
    -0.39
    時代に
    -0.39
    BibitemOpen
    -0.38
     Medicinal
    -0.38
    entingan
    -0.38
     tiens
    -0.38
    处的
    -0.37
    POSITIVE LOGITS
     same
    0.80
    same
    0.73
    Same
    0.71
     Same
    0.68
     similar
    0.63
     Мексичка
    0.61
     mesma
    0.60
     gleichen
    0.60
    SAME
    0.57
     SAME
    0.56
    Act Density 0.078%

    No Known Activations