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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references to court procedures or rulings

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

    summary order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rings
    -0.42
     word
    -0.36
    さまざま
    -0.35
     taste
    -0.32
    RUCT
    -0.32
     fils
    -0.32
     Zweifel
    -0.32
     sentiments
    -0.31
     mingling
    -0.31
     beginnetje
    -0.31
    POSITIVE LOGITS
    parsedMessage
    0.78
    ReusableCell
    0.60
     snippetHide
    0.58
    AndEndTag
    0.57
    SequentialGroup
    0.56
    ########.
    0.55
     ब्रेकडाउन
    0.53
     sederhana
    0.53
     Britannia
    0.52
     einfachen
    0.48
    Act Density 0.052%

    No Known Activations