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

    Neuronpedia

    INDEX
    Explanations

    instances of opening parentheses in text

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

    figure labels (A, B, C, D, E)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     separación
    -0.49
     tirantes
    -0.46
     almohada
    -0.45
     navideñas
    -0.45
     redacción
    -0.45
     rodilla
    -0.44
     Infór
    -0.44
     negociación
    -0.43
    "]));
    -0.43
    ())));
    -0.43
    POSITIVE LOGITS
     estekak
    0.73
     (
    0.63
     ("
    0.57
    (
    0.56
     "
    0.56
     (“
    0.54
     }^{[
    0.53
    (“
    0.52
     “
    0.52
    exc
    0.52
    Act Density 0.163%

    No Known Activations