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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and anecdotes

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

    Follows "this," "that," or a contraction

    np_acts-logits-general · gemini-2.0-flash

    this blog definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.56
    WebElementEntity
    -0.48
    sikker
    -0.47
     operativos
    -0.46
    ftagPool
    -0.45
    ỡng
    -0.44
    Coordonnées
    -0.44
     otomatig
    -0.44
     sikkert
    -0.43
    midler
    -0.43
    POSITIVE LOGITS
    CrossRef
    0.49
    makeConstraints
    0.47
    Opinion
    0.46
     Ause
    0.45
    opinion
    0.44
     useAuth
    0.41
     satirical
    0.41
    NOPQRST
    0.40
     Gat
    0.40
     uParam
    0.39
    Act Density 0.273%

    No Known Activations