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

    Neuronpedia

    INDEX
    Explanations

    references to legal concepts and processes

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

    Follows adverbs of simplicity

    np_acts-logits-general · gemini-2.0-flash

    simply, just, only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    -0.68
     especially
    -0.55
    DotNetBar
    -0.51
     precisely
    -0.51
     ALSO
    -0.51
    Also
    -0.51
     '\\;'
    -0.50
     particularly
    -0.50
     myös
    -0.50
     auch
    -0.49
    POSITIVE LOGITS
     saja
    0.96
    而已
    0.89
     thôi
    0.88
    单纯
    0.88
     simplement
    0.85
    simply
    0.84
     suffit
    0.82
     Simplemente
    0.80
     basta
    0.80
     semplici
    0.80
    Act Density 0.306%

    No Known Activations