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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and concepts

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

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.01
    EndInit
    -0.93
    TagMode
    -0.85
     للاسماء
    -0.84
    <unused51>
    -0.84
    <unused23>
    -0.83
    <unused74>
    -0.83
    <unused8>
    -0.83
    <unused79>
    -0.83
    <unused14>
    -0.83
    POSITIVE LOGITS
     ret
    0.33
    -
    0.31
     
    0.30
    <eos>
    0.30
     I
    0.28
    ➯
    0.28
    ↵↵
    0.28
     افتراض
    0.28
     min
    0.27
     n
    0.27
    Act Density 0.012%

    No Known Activations