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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and sentence endings

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

    Followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    sentence endings often followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كامل
    -0.73
    gdx
    -0.68
    ]<<"
    -0.68
     jScrollPane
    -0.67
    **/
    -0.63
     jLabel
    -0.63
    Kjelder
    -0.62
     Soccerway
    -0.61
     jPanel
    -0.61
    商品説明
    -0.60
    POSITIVE LOGITS
     meisten
    0.77
    Choosing
    0.76
    Many
    0.76
     plupart
    0.76
    Chances
    0.74
     fleste
    0.74
     many
    0.73
     Nowadays
    0.72
     Many
    0.72
     Chances
    0.71
    Act Density 0.280%

    No Known Activations