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

    Neuronpedia

    INDEX
    Explanations

    faction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gaz
    -0.07
    rowth
    -0.06
    Gran
    -0.06
    ordination
    -0.06
    Concat
    -0.06
     шир
    -0.06
    Dir
    -0.06
    рг
    -0.06
     moyen
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     factions
    0.14
     faction
    0.14
     Faction
    0.10
     caucus
    0.08
    action
    0.07
    954
    0.07
       
    0.07
     tendencies
    0.07
     enclave
    0.06
     Caucus
    0.06
    Act Density 0.004%

    No Known Activations