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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters related to compliance and conformity

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

    mutual relative matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biais
    -0.53
    Einsatz
    -0.49
    <?
    -0.46
     incorporado
    -0.46
     المعيارى
    -0.46
     Turi
    -0.46
    newData
    -0.45
    ließlich
    -0.44
    发表于
    -0.44
    OURCES
    -0.44
    POSITIVE LOGITS
    相
    2.44
     相
    1.93
     tương
    0.92
    不相
    0.92
    相對
    0.81
     relative
    0.80
    相对
    0.78
     saling
    0.72
     상
    0.69
    相互
    0.67
    Act Density 0.001%

    No Known Activations