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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing processes or developments

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

    upcoming events, descriptions, or future states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jména
    -0.39
    🔕
    -0.36
     Administrativna
    -0.35
     Kró
    -0.35
     actionMode
    -0.34
    refour
    -0.34
     المعيارى
    -0.34
     kral
    -0.33
     acuarela
    -0.33
     ofrec
    -0.33
    POSITIVE LOGITS
    SuspendLayout
    0.52
    parsedMessage
    0.51
    ьаж
    0.50
    gtest
    0.45
    WireFormatLite
    0.45
     upcoming
    0.45
     doInBackground
    0.44
    dAtA
    0.44
    EnableWeb
    0.44
     noDo
    0.44
    Act Density 0.027%

    No Known Activations