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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UI
    -0.07
     drinking
    -0.07
     bad
    -0.07
    -0.06
    bew
    -0.06
     při
    -0.06
     publishing
    -0.06
    sticks
    -0.06
     stick
    -0.06
     padding
    -0.06
    POSITIVE LOGITS
     Largest
    0.07
    истем
    0.06
     standings
    0.06
    ूचन
    0.06
    brıs
    0.06
     Gupta
    0.06
    _Vector
    0.06
     จำ
    0.06
    <HashMap
    0.06
    /art
    0.06
    Act Density 0.008%

    No Known Activations