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

    Neuronpedia

    INDEX
    Explanations

    apocalypse, world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Renaissance
    -0.07
     Ceramic
    -0.06
     chants
    -0.06
     Rena
    -0.06
     松
    -0.06
     Retro
    -0.06
     hay
    -0.06
     ceramic
    -0.06
    ания
    -0.06
    network
    -0.06
    POSITIVE LOGITS
     apocalypse
    0.08
    ocalyptic
    0.08
     Apocalypse
    0.08
    ALER
    0.07
     Terminator
    0.07
    ocalypse
    0.07
     proceedings
    0.07
    OfWork
    0.06
    	em
    0.06
    oot
    0.06
    Act Density 0.007%

    No Known Activations