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

    Neuronpedia

    INDEX
    Explanations

    negations or the word "not"

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

    Follows "Not" (negation)

    np_acts-logits-general · gemini-2.0-flash

    not only, not just, not surprisingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.83
    MemoryWarning
    -0.82
    httphttps
    -0.79
    IntoConstraints
    -0.71
     alcun
    -0.69
    richTextPanel
    -0.68
     alcuna
    -0.67
    SharedDtor
    -0.67
    GEBURTSDATUM
    -0.66
     يتيمه
    -0.66
    POSITIVE LOGITS
     just
    0.57
     least
    0.56
    Just
    0.55
     too
    0.54
    Not
    0.53
     not
    0.52
     quite
    0.51
     Not
    0.51
     Just
    0.50
     knowing
    0.49
    Act Density 0.135%

    No Known Activations