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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structure and processing characteristics

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

    function name objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.96
     المعيارى
    -0.88
    OGND
    -0.88
     kasarigan
    -0.86
     CreateTagHelper
    -0.83
     AssemblyVersion
    -0.82
     queſta
    -0.79
    MessageOf
    -0.77
    __':
    -0.77
     Wicidata
    -0.77
    POSITIVE LOGITS
    speed
    0.32
     break
    0.30
    ↵↵
    0.30
     seg
    0.29
    <eos>
    0.29
    şı
    0.29
    si
    0.28
     mosso
    0.28
    start
    0.28
    ¿
    0.28
    Act Density 0.171%

    No Known Activations