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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in text

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

    apache commons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.57
    +#+#
    -0.48
     duquel
    -0.48
     Infórmanos
    -0.46
    DoubleQuotes
    -0.45
     suspendu
    -0.44
    Javadoc
    -0.42
     ProtoMessage
    -0.40
    surat
    -0.40
    Parcelize
    -0.40
    POSITIVE LOGITS
    Portale
    0.47
    lawayo
    0.44
    Portail
    0.43
    ✥
    0.42
    tedrale
    0.39
    ’
    0.38
    フジテレビ
    0.37
    vě
    0.37
    <eos>
    0.37
    catore
    0.37
    Act Density 0.015%

    No Known Activations