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

    Neuronpedia

    INDEX
    Explanations

    due

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of outstanding financial obligations—words indicating sums owed or due (e.g., “due,” “unpaid,” “remaining,” “sums”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Leather
    -0.08
    Ion
    -0.07
     Ion
    -0.07
    avana
    -0.07
     liegt
    -0.07
     SHALL
    -0.06
     small
    -0.06
     prayer
    -0.06
     ]);↵
    -0.06
    ounsel
    -0.06
    POSITIVE LOGITS
     reconnect
    0.07
     dlg
    0.07
    алог
    0.07
    bee
    0.06
     подключ
    0.06
    стика
    0.06
    .setDate
    0.06
    ofday
    0.06
    ForResource
    0.06
     dong
    0.06
    Act Density 0.005%

    No Known Activations