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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Representation
    -0.07
     همین
    -0.07
    _barrier
    -0.06
     bytecode
    -0.06
    cidade
    -0.06
     tarea
    -0.06
     initiative
    -0.06
     ByteString
    -0.06
     esto
    -0.06
    αι
    -0.06
    POSITIVE LOGITS
    Interior
    0.06
     reportedly
    0.06
     aster
    0.06
    decimal
    0.06
    ेदन
    0.06
    .webdriver
    0.06
     moistur
    0.06
     panic
    0.06
    hiba
    0.06
    bar
    0.06
    Act Density 0.011%

    No Known Activations