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

    Neuronpedia

    INDEX
    Explanations

    references to signed documents or agreements

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

    signed or signed variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.54
    AnimationsModule
    -0.53
    ValueStyle
    -0.50
     Folly
    -0.48
    fferty
    -0.48
     estekak
    -0.47
    facility
    -0.46
    chaun
    -0.46
    CONTROLLER
    -0.45
    舺
    -0.45
    POSITIVE LOGITS
     signed
    2.41
    Signed
    2.30
     Signed
    2.28
    signed
    2.17
    SIGNED
    1.66
     signé
    1.41
     unsigned
    1.34
     firmado
    1.22
     signing
    1.19
     подписа
    1.19
    Act Density 0.012%

    No Known Activations