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

    Neuronpedia

    INDEX
    Explanations

    email addresses and related formatting

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

    email addresses with at or @

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.43
    ngdoc
    -0.37
    Carreira
    -0.36
    EIF
    -0.35
     defaultstate
    -0.35
    reportWebVitals
    -0.32
    ulto
    -0.32
    嘧
    -0.31
    robo
    -0.30
    expandindo
    -0.30
    POSITIVE LOGITS
     Италијани
    0.58
    msgTypes
    0.56
    kloped
    0.53
     intStringLen
    0.50
    værende
    0.49
    tplatz
    0.49
    ésultats
    0.47
    GenerationType
    0.47
    imageshack
    0.47
     povezave
    0.46
    Act Density 0.023%

    No Known Activations