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

    Neuronpedia

    INDEX
    Explanations

    instances of the output stream commands in code

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

    Code or file paths

    np_acts-logits-general · gemini-2.0-flash

    code and numbers following `user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.65
     proyección
    -0.59
     paja
    -0.59
     Comprometido
    -0.59
     curiosidad
    -0.58
     solidaridad
    -0.58
     antemano
    -0.57
     Lösungs
    -0.56
    //
    -0.56
     ganchillo
    -0.56
    POSITIVE LOGITS
     كومونز
    0.40
     ВА
    0.31
    XmlAccessType
    0.29
    々
    0.29
    {}\
    0.29
    事
    0.29
     Michael
    0.29
     سكانية
    0.28
     Oo
    0.28
     Nh
    0.28
    Act Density 1.107%

    No Known Activations