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

    Neuronpedia

    INDEX
    Explanations

    negations and assertions of impossibility or lack

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

    "no" followed by a negative word

    np_acts-logits-general · gemini-2.0-flash

    "no" followed by a noun indicating absence or certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appena
    -0.59
     Roskov
    -0.55
    たまたま
    -0.55
    IsContent
    -0.54
     ISTAT
    -0.53
    httphttps
    -0.53
     remarquer
    -0.53
     immerhin
    -0.52
    ValueStyle
    -0.51
     fédéral
    -0.50
    POSITIVE LOGITS
     reason
    0.77
     point
    0.75
     way
    0.71
    ⓧ
    0.64
    addGap
    0.63
     better
    0.62
     guarantee
    0.62
     escaping
    0.61
     utafitiHapana
    0.61
    TypedDataSet
    0.61
    Act Density 0.167%

    No Known Activations