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

    Neuronpedia

    INDEX
    Explanations

    sequences of tabbed spaces or empty segments in the document

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

    parentheses and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.44
    fact
    -0.38
    styleUrls
    -0.37
    HR
    -0.37
    ähr
    -0.35
    Ign
    -0.35
    utri
    -0.35
    EOL
    -0.35
    goog
    -0.35
    ValueStyle
    -0.35
    POSITIVE LOGITS
    uxxxx
    0.81
    دانشنامهٔ
    0.60
    Fordítás
    0.59
    BagConstraints
    0.57
    Rohy
    0.56
     Normdatei
    0.53
     Biôgrafia
    0.49
    Viitteet
    0.49
     Geiſt
    0.49
     ?$
    0.48
    Act Density 0.014%

    No Known Activations