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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mix
    -0.07
     Automobile
    -0.06
     εμφ
    -0.06
     úrov
    -0.06
     production
    -0.06
     pulp
    -0.06
    Substring
    -0.06
     condemning
    -0.06
    бав
    -0.06
    一般
    -0.06
    POSITIVE LOGITS
     Sadly
    0.07
     elders
    0.07
    ashire
    0.06
    .StoredProcedure
    0.06
    .Click
    0.06
     Ấn
    0.06
     Kürt
    0.06
    IBUTES
    0.06
    (updated
    0.06
    arians
    0.06
    Act Density 0.047%

    No Known Activations