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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values associated with data or statistics

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

    year dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tuvo
    -0.34
     mencionado
    -0.33
     прошлого
    -0.32
    ,
    -0.32
     Consulte
    -0.31
     hábiles
    -0.31
    following
    -0.31
     Vorg
    -0.30
     aquel
    -0.30
     sammen
    -0.29
    POSITIVE LOGITS
     ſind
    0.90
     Efq
    0.80
     queſta
    0.71
    fjspx
    0.70
     ſei
    0.68
     agendas
    0.68
    MarshalTo
    0.67
    transQ
    0.65
     ་་
    0.65
     ſehr
    0.64
    Act Density 0.018%

    No Known Activations