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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in programming or code syntax

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

    code validations and field definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.92
     myſelf
    -0.79
     Theſe
    -0.77
     EconPapers
    -0.77
    ロウィン
    -0.77
    setVerticalGroup
    -0.76
    majánló
    -0.76
    <unused74>
    -0.74
    [@BOS@]
    -0.74
    <unused14>
    -0.74
    POSITIVE LOGITS
    (:
    0.59
    ://
    0.52
    ↵
    0.50
     '
    0.50
     "
    0.49
     «
    0.46
    ('
    0.44
    [:
    0.44
    (&:
    0.42
    ↵↵
    0.42
    Act Density 0.004%

    No Known Activations