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

    Neuronpedia

    INDEX
    Explanations

    references to decisions or announcements regarding appointments and approvals

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

    Followed by "will" or "has"

    np_acts-logits-general · gemini-2.0-flash

    future actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    后来
    -0.49
    때
    -0.48
    rías
    -0.48
     때
    -0.48
     kontin
    -0.48
     Lately
    -0.47
     тогда
    -0.47
    érie
    -0.46
     selalu
    -0.45
    НИК
    -0.45
    POSITIVE LOGITS
     will
    0.93
    SequentialGroup
    0.88
    これで
    0.87
    这下
    0.78
     propOrder
    0.77
     künftig
    0.77
     potrà
    0.75
    will
    0.74
     potranno
    0.74
     gonna
    0.72
    Act Density 0.304%

    No Known Activations