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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.53
    "}},
    -0.53
    has
    -0.47
    "}}
    -0.47
    NOPQRST
    -0.46
    tuvo
    -0.46
    Has
    -0.45
    }}{{
    -0.45
    DoubleQuotes
    -0.44
    "}
    -0.44
    POSITIVE LOGITS
    ugeot
    0.68
    AsUp
    0.68
    UserScript
    0.63
     للمعارف
    0.60
    modity
    0.57
     nothing
    0.56
     court
    0.56
    σθαι
    0.55
    Autoritní
    0.55
     They
    0.54
    Act Density 0.000%

    No Known Activations