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

    Neuronpedia

    INDEX
    Explanations

    verbs related to limitation or obstruction

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

    preventing or hindering actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.54
     betweenstory
    -0.48
    expandindo
    -0.46
     виправивши
    -0.42
    cticut
    -0.42
    InjectAttribute
    -0.42
    دانشنامهٔ
    -0.41
    ValueStyle
    -0.41
    يميديا
    -0.40
     ویکی‌پدی
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.56
     utafitiHapana
    0.49
    Nonetheless
    0.48
     Nonetheless
    0.47
     EconPapers
    0.47
     nonetheless
    0.44
    sunter
    0.43
    Nevertheless
    0.43
    atimes
    0.43
    despite
    0.41
    Act Density 0.032%

    No Known Activations