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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the phrase “works for us” (or close variants expressing that something “works for us/both of us”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stdout
    -0.07
     smash
    -0.06
     elt
    -0.06
    енную
    -0.06
    aces
    -0.06
     设
    -0.06
     MacBook
    -0.06
    Employ
    -0.06
    拓
    -0.06
     dances
    -0.06
    POSITIVE LOGITS
    urnal
    0.07
     empirical
    0.06
    issional
    0.06
     fairness
    0.06
    (TABLE
    0.06
    JV
    0.06
     whatever
    0.06
     Rio
    0.06
     rooted
    0.06
     served
    0.06
    Act Density 0.008%

    No Known Activations