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

    Neuronpedia

    INDEX
    Explanations

    terms related to relationships and roles

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

    係長, 関係, Hallmark Christmas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁮
    -0.49
    WriteTagHelper
    -0.46
     Corro
    -0.44
    Nobel
    -0.41
    PREFERRED
    -0.41
     adidas
    -0.41
     Tartar
    -0.41
     corti
    -0.40
     Memor
    -0.40
     lond
    -0.40
    POSITIVE LOGITS
    系
    2.44
    系的
    1.73
    系の
    1.73
     系
    1.71
    계
    1.28
     hệ
    1.05
     계
    0.98
    繫
    0.95
     Hệ
    0.84
    系列
    0.84
    Act Density 0.003%

    No Known Activations