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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly those with the name "Fr."

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

    starting with "fr" or "FR"

    np_acts-logits-general · gemini-2.0-flash

    words starting with fr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rested
    -0.60
    apsed
    -0.58
    Còn
    -0.56
     tourné
    -0.54
     rest
    -0.54
    footed
    -0.52
     Romains
    -0.52
    ulatum
    -0.51
     footnote
    -0.51
     Basso
    -0.50
    POSITIVE LOGITS
     FR
    0.84
     FRE
    0.83
     GenerationType
    0.77
     BoxFit
    0.75
     Frig
    0.73
     FetchType
    0.73
     frater
    0.73
     Franch
    0.72
     fré
    0.72
     للمعارف
    0.71
    Act Density 0.126%

    No Known Activations