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

    Neuronpedia

    INDEX
    Explanations

    actions and abilities expressed through the verb "can."

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

    actions you can take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.60
    üyada
    -0.56
    RegressionTest
    -0.54
     propOrder
    -0.52
    endphp
    -0.52
    berdayakan
    -0.51
     betweenstory
    -0.51
    SourceChecksum
    -0.50
    tonode
    -0.50
     kohdetta
    -0.48
    POSITIVE LOGITS
     can
    0.42
     online
    0.42
     digital
    0.41
     gau
    0.41
     corresponding
    0.40
    andReturn
    0.39
     mailing
    0.37
     official
    0.37
    dostęp
    0.37
     email
    0.36
    Act Density 0.017%

    No Known Activations