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

    Neuronpedia

    INDEX
    Explanations

    closing braces and semicolons in code

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

    program code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เปล
    -0.36
     can
    -0.35
    リーン
    -0.33
     see
    -0.30
     sh
    -0.29
     ap
    -0.28
     support
    -0.28
     clean
    -0.28
     Wille
    -0.28
     otherwise
    -0.27
    POSITIVE LOGITS
    hoeddwyd
    0.82
    новништво
    0.78
    󠁿
    0.73
     насељу
    0.72
    WriteTagHelper
    0.72
    Diweddarwch
    0.72
    EDEFAULT
    0.72
    endphp
    0.71
    GOTREF
    0.70
     nahilalakip
    0.69
    Act Density 0.167%

    No Known Activations