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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing conditions or options in decision-making scenarios

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

    alternatives or next steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solches
    -0.43
    IfNeeded
    -0.42
     näin
    -0.40
     Hivatalos
    -0.40
    しかも
    -0.40
    SourceChecksum
    -0.39
     including
    -0.39
    而非
    -0.38
     sekä
    -0.38
     zarówno
    -0.38
    POSITIVE LOGITS
    没关系
    0.79
     then
    0.74
     alternative
    0.63
     still
    0.59
     alternatively
    0.59
    then
    0.58
     alternatif
    0.57
    alternative
    0.57
    Alternative
    0.56
    Then
    0.55
    Act Density 0.035%

    No Known Activations