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

    Neuronpedia

    INDEX
    Explanations

    ',

    np_max-act · gemini-2.0-flash

    This neuron detects references to the “tool” selection list or tool-related headings in the instruction text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wars
    -0.07
    SKU
    -0.07
     ↵            ↵
    -0.07
     motives
    -0.07
     Wright
    -0.07
     Save
    -0.06
     choir
    -0.06
     rivals
    -0.06
    มา
    -0.06
     hated
    -0.06
    POSITIVE LOGITS
    uppe
    0.07
    .tabPage
    0.07
    dialog
    0.07
     Harmon
    0.06
    užel
    0.06
    raising
    0.06
    @FindBy
    0.06
     leth
    0.06
    09
    0.06
    .toolStripMenuItem
    0.06
    Act Density 0.001%

    No Known Activations