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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions and modifiers that indicate frequency or typicality

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

    commonality or frequency

    np_acts-logits-general · gemini-2.0-flash

    usual or typical actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possibly
    -0.67
     potentially
    -0.66
    possibly
    -0.59
    potentially
    -0.58
     möglicherweise
    -0.57
     conceivably
    -0.55
     pernah
    -0.55
    maybe
    -0.53
    いいのか
    -0.53
     maybe
    -0.52
    POSITIVE LOGITS
    abestanden
    0.75
    情况下
    0.68
    ὖ
    0.66
    -------------</
    0.66
     bý
    0.65
     suele
    0.65
     noDo
    0.63
     iNdEx
    0.62
    accompanied
    0.62
    oluene
    0.61
    Act Density 0.387%

    No Known Activations