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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qi
    -0.07
    cout
    -0.07
    mall
    -0.06
    conexao
    -0.06
     Julio
    -0.06
    kt
    -0.06
     loa
    -0.06
     discern
    -0.06
    rances
    -0.06
    -x
    -0.06
    POSITIVE LOGITS
     AudioManager
    0.07
    Fight
    0.07
     gunfire
    0.06
     Quant
    0.06
     synonyms
    0.06
    phoon
    0.06
     preceding
    0.06
     Biological
    0.06
    лон
    0.06
     розрах
    0.06
    Act Density 0.002%

    No Known Activations