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

    Neuronpedia

    INDEX
    Explanations

    references to social responsibility and relationship dynamics

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

    just as comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.46
    tangentMode
    -0.44
    UrlResolution
    -0.44
     الرياضيه
    -0.43
    хівовано
    -0.43
     extrême
    -0.43
    visuel
    -0.43
    Географиясе
    -0.43
    pfung
    -0.42
     propOrder
    -0.41
    POSITIVE LOGITS
    Exactly
    0.47
    just
    0.46
    exactly
    0.44
    JUST
    0.43
     JUST
    0.43
    Just
    0.41
     Mira
    0.40
     just
    0.40
     iprot
    0.40
     Just
    0.40
    Act Density 0.017%

    No Known Activations