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

    Neuronpedia

    INDEX
    Explanations

    mathematical and formatting symbols used in coding and document preparation

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

    mathematical notation and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     citoy
    -0.46
     juges
    -0.41
     bowiem
    -0.40
     nemlig
    -0.39
     hábiles
    -0.38
     Emple
    -0.38
     inmig
    -0.37
     Sebab
    -0.37
     documentación
    -0.37
     aldea
    -0.36
    POSITIVE LOGITS
    =\
    0.84
    ))=\
    0.75
     autorytatywna
    0.71
    |=\
    0.71
    &=\
    0.67
    ]=\
    0.66
     =\
    0.64
    )=\
    0.64
     للمعارف
    0.61
     $=\
    0.61
    Act Density 0.004%

    No Known Activations