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

    Neuronpedia

    INDEX
    Explanations

    repeated numerical values or patterns

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ndez
    -0.49
    avoit
    -0.48
     segi
    -0.47
    fix
    -0.46
    Trọng
    -0.44
    NewUrlParser
    -0.44
     længere
    -0.44
     auttaa
    -0.44
    dir
    -0.43
     päiv
    -0.43
    POSITIVE LOGITS
     vv
    0.57
    shadowOpacity
    0.56
     resourceCulture
    0.56
     ttk
    0.56
     pprint
    0.55
    0.50
    Mucha
    0.50
    0.50
     YY
    0.50
     addUser
    0.49
    Act Density 0.029%

    No Known Activations