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

    Neuronpedia

    INDEX
    Explanations

    names and relationships among characters

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

    specific prefixes and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.50
    :✨
    -0.43
     "];
    -0.41
    ])]
    -0.38
    __);
    -0.37
    ]]
    -0.37
     ""],
    -0.36
    ']],
    -0.36
    庁
    -0.36
    +");
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.52
    bParam
    0.52
    expandindo
    0.52
     Վերցված
    0.50
    ExtendWith
    0.49
    Chham
    0.48
     pageContext
    0.48
    Diweddarwch
    0.47
     cref
    0.46
    fileID
    0.45
    Act Density 0.023%

    No Known Activations