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

    Neuronpedia

    INDEX
    Explanations

    names or references to specific people or entities

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

    "Lu" followed by other characters or words

    np_acts-logits-general · gemini-2.0-flash

    Lu followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.82
     Monfieur
    -0.82
     reaſon
    -0.76
     themſelves
    -0.73
     pleaſure
    -0.73
     poffible
    -0.72
     myſelf
    -0.72
     Majefty
    -0.71
     greateſt
    -0.70
     houſe
    -0.66
    POSITIVE LOGITS
     Lu
    0.76
     lu
    0.74
     calendriers
    0.65
    Lu
    0.61
     lut
    0.59
    lu
    0.58
     Lucre
    0.58
     الحره
    0.56
     Lut
    0.56
     luc
    0.55
    Act Density 0.131%

    No Known Activations