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
     warehouse
    -0.07
     WAR
    -0.07
    uhan
    -0.06
     kvp
    -0.06
     Kü
    -0.06
    ===========
    -0.06
    belongs
    -0.06
     Lud
    -0.06
     temperatura
    -0.06
    PRESS
    -0.06
    POSITIVE LOGITS
     report
    0.06
    _agents
    0.06
    enses
    0.06
    “그
    0.06
    walking
    0.06
    ensis
    0.06
    tips
    0.06
     Valle
    0.06
     delicious
    0.06
     هنگ
    0.06
    Act Density 0.000%

    No Known Activations