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

    Neuronpedia

    INDEX
    Explanations

    annotation identification

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the process of identifying or annotating (e.g. “annotation,” “identification,” “identified”) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sigma
    -0.07
     Quit
    -0.06
    Neighbor
    -0.06
    acho
    -0.06
    XC
    -0.06
    cycle
    -0.06
     preferred
    -0.06
    _plane
    -0.06
     неї
    -0.06
     probes
    -0.06
    POSITIVE LOGITS
    重要
    0.07
     hry
    0.06
    -↵
    0.06
    ایی
    0.06
    ónica
    0.06
     duygu
    0.06
    vk
    0.06
    vrir
    0.06
    $")↵
    0.06
    stant
    0.06
    Act Density 0.005%

    No Known Activations