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

    Neuronpedia

    INDEX
    Explanations

    curly braces and other closing symbols in code structures

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

    code closing braces and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -0.63
    audiovisuel
    -0.60
     queſta
    -0.60
    granate
    -0.59
    oa̍t
    -0.58
     NSError
    -0.58
    <unused47>
    -0.57
     ✭✭
    -0.57
    [@BOS@]
    -0.57
    رشف
    -0.57
    POSITIVE LOGITS
     mourut
    0.41
     vœ
    0.40
     heridos
    0.38
     herido
    0.38
     cubierto
    0.38
    DockStyle
    0.38
     équilibr
    0.36
     cumplido
    0.36
     navideño
    0.35
     ferdig
    0.35
    Act Density 0.010%

    No Known Activations