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

    Neuronpedia

    INDEX
    Explanations

    Business/technical contexts

    np_max-act · gemini-2.0-flash

    This neuron activates on present‐participle (-ing) action verbs, especially those that begin instruction or list items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Archbishop
    -0.07
    `).
    -0.06
     Üst
    -0.06
     winter
    -0.06
    ức
    -0.06
     hips
    -0.06
    Histor
    -0.06
     پست
    -0.06
    .nodeType
    -0.06
    -described
    -0.06
    POSITIVE LOGITS
     jung
    0.06
    zar
    0.06
    ategory
    0.06
    herence
    0.06
     tirelessly
    0.06
    /↵↵
    0.06
    ternal
    0.06
    لفة
    0.06
    .ToolStripSeparator
    0.06
    (Blueprint
    0.06
    Act Density 0.167%

    No Known Activations