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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    keywords and actions related to software functionality and features.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ="")↵
    -0.07
     marginal
    -0.07
     majestic
    -0.07
    Debe
    -0.06
     resumed
    -0.06
     Cait
    -0.06
    んでいる
    -0.06
    /compiler
    -0.06
     little
    -0.06
    .Orientation
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    ILLE
    0.07
    .puts
    0.06
    Ả
    0.06
    hecy
    0.06
    _REC
    0.06
    찬
    0.06
     GET
    0.06
    ούν
    0.06
    _pending
    0.06
    Act Density 0.122%

    No Known Activations