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

    Neuronpedia

    INDEX
    Explanations

    certain punctuation marks and sentence structures

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

    initials followed by entity or citation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.55
    Portály
    -0.53
     PhpStorm
    -0.50
     مشين
    -0.49
    المناصب
    -0.48
    -0.48
    ReusableCell
    -0.46
     snippetHide
    -0.45
    뀜
    -0.44
     Privacidade
    -0.44
    POSITIVE LOGITS
     KB
    0.42
    BJ
    0.42
     BD
    0.40
    Ƚ
    0.40
    ODB
    0.39
     VD
    0.39
    횟
    0.39
     LM
    0.39
    oyd
    0.39
     Bob
    0.39
    Act Density 0.072%

    No Known Activations