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

    Neuronpedia

    INDEX
    Explanations

    opening and closing braces in code snippets

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

    code, errors, and general programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PhysRev
    -0.58
    IMPORTED
    -0.52
     crossorigin
    -0.49
    \/
    -0.46
    ▬▬▬▬▬▬▬▬
    -0.46
    glVertex
    -0.44
    ↵↵↵
    -0.44
     √
    -0.44
    nextToken
    -0.43
     Anderson
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.63
    :{
    0.61
     sequência
    0.58
    __":
    0.57
     Bewußt
    0.56
     financeira
    0.56
     Geheimnis
    0.55
    ::{
    0.54
    ":{
    0.54
    ':{
    0.52
    Act Density 0.014%

    No Known Activations