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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to software and implementation issues

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

    Code, URLs, or file paths

    np_acts-logits-general · gemini-2.0-flash

    speech intelligibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.49
    NameInMap
    -0.48
    GOTREF
    -0.43
     Мексичка
    -0.43
    xase
    -0.42
     MenuView
    -0.42
    بوابة
    -0.41
    原始内容存档于
    -0.38
     ProtoMessage
    -0.37
    wild
    -0.37
    POSITIVE LOGITS
     retired
    0.41
     eint
    0.41
    ServiceTest
    0.40
     pemer
    0.39
     producenta
    0.39
     disfruta
    0.38
     terecht
    0.38
     emailed
    0.38
     lezen
    0.37
    pisah
    0.37
    Act Density 0.915%

    No Known Activations