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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and functions

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

    writing buffers or streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.40
     
    -0.38
    ↵
    -0.38
    <eos>
    -0.35
    startX
    -0.33
    PLIC
    -0.33
      
    -0.32
    #
    -0.32
     Schäfer
    -0.32
    clientX
    -0.31
    POSITIVE LOGITS
    Personendaten
    1.01
    ChildScrollView
    0.93
    IndentedString
    0.86
     المعيارى
    0.85
    +#+
    0.85
     متعلقه
    0.83
    GOTREF
    0.81
    <unused23>
    0.80
    <unused16>
    0.80
    <unused3>
    0.80
    Act Density 0.016%

    No Known Activations