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

    Neuronpedia

    INDEX
    Explanations

    linked list definitions and listening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moraes
    0.40
    vig
    0.36
    листи
    0.36
     Mél
    0.35
    璐
    0.35
    ("../../
    0.35
    weł
    0.35
     ceremonies
    0.35
     Trilogy
    0.34
    onRouteChange
    0.34
    POSITIVE LOGITS
    Ა
    0.39
     pion
    0.36
     eviden
    0.36
     తమ
    0.35
    젠
    0.35
    🤌
    0.35
     impar
    0.35
     Wendy
    0.34
     aead
    0.34
    तिम
    0.34
    Act Density 0.003%

    No Known Activations