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

    Neuronpedia

    INDEX
    Explanations

    elements of programming or data structure definitions

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

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -1.00
    ロウィン
    -0.84
     يتيمه
    -0.79
     utafitiHapana
    -0.78
    <unused41>
    -0.75
    ſelben
    -0.74
    WriteTagHelper
    -0.74
    <unused74>
    -0.74
    <unused16>
    -0.74
    <unused23>
    -0.74
    POSITIVE LOGITS
    <eos>
    0.58
     mentioned
    0.31
     eventual
    0.30
    ↵↵
    0.29
     mencionado
    0.28
     etc
    0.28
     Kommun
    0.28
     noted
    0.27
    …
    0.25
    </blockquote>
    0.25
    Act Density 0.077%

    No Known Activations