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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences involving mathematical symbols and structure

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

    characteristics of interventions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.62
    HtmlAttribute
    -0.52
    ]-->
    -0.51
    pture
    -0.50
    rosoft
    -0.49
    archiviato
    -0.49
     BoxFit
    -0.48
    lccn
    -0.47
    $_['
    -0.46
    andExpect
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.45
    Erstellt
    0.39
     uLocal
    0.39
     defaultstate
    0.38
     Personalis
    0.37
     desconocido
    0.36
     sonriendo
    0.36
    UnusedPrivate
    0.35
     remarquable
    0.35
    ografija
    0.35
    Act Density 0.061%

    No Known Activations