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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and declarations in code

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

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -1.01
     beſte
    -0.89
    Билгалдахарш
    -0.88
    -0.88
    RTSC
    -0.87
    <unused43>
    -0.86
    GOTREF
    -0.86
    <unused41>
    -0.85
    <unused8>
    -0.85
    [@BOS@]
    -0.85
    POSITIVE LOGITS
    ↵
    0.25
    ↵↵
    0.24
     others
    0.22
     recomand
    0.21
     then
    0.21
     galeri
    0.21
     ,
    0.20
    ידות
    0.20
     |
    0.20
     bagay
    0.20
    Act Density 0.084%

    No Known Activations