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

    Neuronpedia

    INDEX
    Explanations

    elements of code structure or syntax definitions

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.76
    AndEndTag
    -0.69
    SharedCtor
    -0.68
     iprot
    -0.64
    transQ
    -0.63
     Италијани
    -0.62
     Administrativna
    -0.60
    DrawerToggle
    -0.59
     propOrder
    -0.59
    SequentialGroup
    -0.59
    POSITIVE LOGITS
     trône
    0.50
     puertos
    0.43
     vœ
    0.42
     État
    0.41
     désert
    0.39
     golfe
    0.38
     Estados
    0.37
     funcionalidad
    0.36
     adquis
    0.36
     témoignage
    0.36
    Act Density 0.001%

    No Known Activations