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

    Neuronpedia

    INDEX
    Explanations

    references to connections and associations in various contexts

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

    Text after uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    mathematical and programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -1.06
     Paglinawan
    -0.95
     Italijanski
    -0.93
     pleaſure
    -0.90
     Majefty
    -0.88
     ſtate
    -0.85
    Filmografie
    -0.84
    Vidite
    -0.84
    GraphicsUnit
    -0.81
     purpoſe
    -0.81
    POSITIVE LOGITS
     […]
    0.60
     …
    0.60
    […]
    0.60
    NOPQRST
    0.53
    ….
    0.50
    .
    0.49
     ….
    0.49
    ↵↵
    0.43
    …
    0.43
    A
    0.41
    Act Density 1.296%

    No Known Activations