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

    Neuronpedia

    INDEX
    Explanations

    Assertions or claims about societal issues and controversies

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

    even with comparatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verwijzen
    -0.45
    Aholisi
    -0.42
     andererseits
    -0.40
     հղումներ
    -0.39
     åter
    -0.38
     dunque
    -0.38
    beforeAll
    -0.37
     فريبيس
    -0.36
    deka
    -0.36
    тельстве
    -0.35
    POSITIVE LOGITS
     sogar
    0.49
     even
    0.49
    even
    0.44
     hatta
    0.44
     még
    0.44
     даже
    0.42
     lagi
    0.41
    additional
    0.40
     additional
    0.40
    EDEFAULT
    0.39
    Act Density 0.083%

    No Known Activations