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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with punctuation marks, particularly periods or quotes

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

    Code, error messages, or names

    np_acts-logits-general · gemini-2.0-flash

    legal jargon and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nonatomic
    -0.57
     HttpNotFound
    -0.53
     _('
    -0.49
    SourceChecksum
    -0.47
     considérons
    -0.47
    kään
    -0.47
    inSlope
    -0.47
    Recommend
    -0.47
    はじめに
    -0.46
    NavController
    -0.46
    POSITIVE LOGITS
    format
    0.68
    findpost
    0.64
    "".
    0.59
    ContentAlignment
    0.59
     متعلقه
    0.55
     DRY
    0.55
    তথ্যসূত্র
    0.54
    Notae
    0.53
    maphore
    0.52
    formin
    0.52
    Act Density 0.082%

    No Known Activations