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

    Neuronpedia

    INDEX
    Explanations

    technical or programming-related keywords and structures

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

    Non-alphanumeric characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    degradation processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addGroup
    -0.50
    eqn
    -0.50
    HasForeignKey
    -0.49
    ])));
    -0.48
     Ch
    -0.47
    FormTagHelper
    -0.44
     &___
    -0.43
     Cha
    -0.42
     Th
    -0.42
    IALLY
    -0.42
    POSITIVE LOGITS
     itſelf
    1.00
    脚注の使い方
    0.86
     crdi
    0.83
     Moslem
    0.72
     tdci
    0.71
    homonymie
    0.71
    disambiguation
    0.70
    0.70
     wikipagina
    0.70
     NDEBUG
    0.69
    Act Density 0.772%

    No Known Activations