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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that explore perceptions or beliefs

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

    Follows "what" or "what was/were."

    np_acts-logits-general · gemini-2.0-flash

    what is or could be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    참고
    -0.66
    UnusedPrivate
    -0.59
    PerformLayout
    -0.59
    DotNetBar
    -0.58
    HasForeignKey
    -0.57
    forKey
    -0.55
    prefixer
    -0.54
    SharedCtor
    -0.53
    Билгалдахарш
    -0.53
    tonode
    -0.52
    POSITIVE LOGITS
     arguably
    0.75
     essentially
    0.70
     otherwise
    0.68
     admittedly
    0.61
     presumably
    0.61
     ostensibly
    0.60
     increasingly
    0.59
     undoubtedly
    0.59
     Waray
    0.59
    おそらく
    0.57
    Act Density 0.084%

    No Known Activations