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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of places and people

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

    Iceland Project, Chicago machine, Bitterwood Bible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marinho
    -0.38
    requested
    -0.36
    ่า
    -0.32
     nationales
    -0.31
    providedIn
    -0.31
     Nasional
    -0.31
    ífer
    -0.31
    haben
    -0.31
    gemene
    -0.30
    zweck
    -0.30
    POSITIVE LOGITS
     дописавши
    0.63
     invokingState
    0.57
     massacre
    0.55
     exor
    0.54
    MemoryWarning
    0.52
     rumble
    0.52
     hustle
    0.52
     يتيمه
    0.52
     vibes
    0.51
     mojo
    0.51
    Act Density 0.044%

    No Known Activations