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

    Neuronpedia

    INDEX
    Explanations

    statistical data and results related to research studies

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

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istoitu
    -0.70
    fjspx
    -0.65
     للمعارف
    -0.62
    RTSC
    -0.62
     ObjectParameter
    -0.59
    IVEREF
    -0.59
     MainAxisSize
    -0.59
    ⤹
    -0.59
    UnusedPrivate
    -0.58
    RTLU
    -0.57
    POSITIVE LOGITS
     communs
    0.41
     kiin
    0.40
     bienes
    0.36
     informacija
    0.35
     Italij
    0.35
     limão
    0.35
     häls
    0.34
     înal
    0.34
     bună
    0.33
     dirigeants
    0.32
    Act Density 0.072%

    No Known Activations