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

    Neuronpedia

    INDEX
    Explanations

    various types of punctuation marks and formatting symbols, indicating structure in text

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

    . or ## followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    insegna
    -0.43
     ennen
    -0.38
     Eink
    -0.37
    C
    -0.37
     unei
    -0.37
    geordnet
    -0.36
    gelöst
    -0.35
     praktijk
    -0.35
    using
    -0.35
    ED
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.81
    ⤹
    0.78
    TagMode
    0.75
    Autoritní
    0.75
     Италијани
    0.73
     noDo
    0.73
    Aholisi
    0.72
     CanadaChoose
    0.67
    :✨
    0.66
    httphttps
    0.65
    Act Density 0.072%

    No Known Activations