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

    Neuronpedia

    INDEX
    Explanations

    elements of code or technical formatting within text

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

    HTML span tag

    np_acts-logits-general · gemini-2.0-flash

    span for formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CrossRef
    -0.73
    sizeCache
    -0.69
    SerializeField
    -0.67
    SharedDtor
    -0.67
     démo
    -0.64
     通販
    -0.63
     Chwiliwch
    -0.62
     Mindset
    -0.61
    Geplaatst
    -0.61
    TypedDataSet
    -0.60
    POSITIVE LOGITS
    ↵↵
    0.73
    enumerate
    0.56
     long
    0.53
    プライズ
    0.52
    ArgumentParser
    0.49
     lunga
    0.45
    long
    0.44
    cove
    0.44
     bParam
    0.44
    backslash
    0.44
    Act Density 0.001%

    No Known Activations