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

    Neuronpedia

    INDEX
    Explanations

    contexts discussing limitations or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    exceeding a boundary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſte
    -0.46
    dataclass
    -0.46
    glise
    -0.46
     ſta
    -0.40
     Artículos
    -0.40
    </thead>
    -0.40
     houſe
    -0.40
     teatr
    -0.40
     $("
    -0.40
     *"
    -0.39
    POSITIVE LOGITS
     beyond
    2.31
    beyond
    2.20
     Beyond
    2.11
     BEYOND
    2.02
    Beyond
    2.02
    YOND
    1.58
    delà
    1.09
    超越
    0.85
    超出
    0.84
    enseits
    0.82
    Act Density 0.006%

    No Known Activations