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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or summarizing findings

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

    conclusion and summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.70
    DockStyle
    -0.69
     يتيمه
    -0.69
    ValueStyle
    -0.59
     zwiſchen
    -0.59
     propOrder
    -0.57
    niſſe
    -0.56
     queſta
    -0.56
    postIndex
    -0.56
    iſchen
    -0.55
    POSITIVE LOGITS
     Summary
    0.38
     conclusión
    0.34
    Summary
    0.33
     summary
    0.32
    证
    0.31
    autaire
    0.31
    writeFieldEnd
    0.30
     concl
    0.30
     Lä
    0.30
    CONCLUS
    0.29
    Act Density 0.078%

    No Known Activations