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

    Neuronpedia

    INDEX
    Explanations

    sections of the document that contain technical or scientific terminology

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

    Prepositions and articles following short tokens

    np_acts-logits-general · gemini-2.0-flash

    Madagascar, Ny, Congo, Rwanda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Alberta
    -0.75
    Alberta
    -0.72
     Vancouver
    -0.61
     Dene
    -0.61
     Calgary
    -0.57
     Banff
    -0.55
     UBC
    -0.54
     Baja
    -0.53
    Punj
    -0.52
     Okan
    -0.52
    POSITIVE LOGITS
     Madagascar
    1.08
    Madagascar
    0.95
    AndEndTag
    0.84
     يتيمه
    0.76
     Ny
    0.73
    Ny
    0.72
     izay
    0.69
     intptr
    0.69
     MonoBehaviour
    0.68
    StoryboardSegue
    0.67
    Act Density 0.043%

    No Known Activations