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

    Neuronpedia

    INDEX
    Explanations

    references to research, citations, and discussions about accuracy or evidence in arguments

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

    distort different more close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     known
    -0.35
    known
    -0.31
     actual
    -0.31
    셔
    -0.28
     Actual
    -0.28
    pad
    -0.28
    Actual
    -0.28
    也许
    -0.27
    du
    -0.27
    index
    -0.27
    POSITIVE LOGITS
     Administrativna
    0.92
     autorytatywna
    0.89
     betweenstory
    0.81
    queryInterface
    0.79
     Numerade
    0.79
     linkovi
    0.79
    Personensuche
    0.78
     صوتيه
    0.74
     Italijanski
    0.71
    parsedMessage
    0.70
    Act Density 0.317%

    No Known Activations