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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and related demonstrative references

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

    this indicates a concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.41
     goddamn
    -0.38
    HasColumnName
    -0.35
    here
    -0.35
    :✨
    -0.34
    ⇀
    -0.34
     bomb
    -0.34
     damn
    -0.33
     shit
    -0.33
     fucking
    -0.33
    POSITIVE LOGITS
     lenker
    0.63
     seda
    0.62
     tłuma
    0.58
     związane
    0.56
     సౌకర్య
    0.56
     Nacionales
    0.55
     felicitación
    0.54
     Hilfs
    0.54
     häufigsten
    0.54
     üblichen
    0.54
    Act Density 0.152%

    No Known Activations