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

    Neuronpedia

    INDEX
    Explanations

    negative contractions and forms of "to be" along with their contexts

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

    negation, absence, never, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Slf
    -0.58
    évaluateur
    -0.58
    fxml
    -0.54
    󠁿
    -0.54
     —
    -0.50
    ]-->
    -0.47
    >
    -0.46
    -0.46
    /*-
    -0.46
    存于互联网档案馆
    -0.45
    POSITIVE LOGITS
     dieß
    0.58
     nigdy
    0.57
     هیچ
    0.54
     nothin
    0.54
     никогда
    0.54
     nikdy
    0.53
     scarcely
    0.52
     neither
    0.52
     never
    0.51
     NOTHING
    0.50
    Act Density 0.012%

    No Known Activations