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

    Neuronpedia

    INDEX
    Explanations

    project

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of specific projects or research initiatives, especially when titled or capitalized.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    notEmpty
    -0.07
     数
    -0.06
    εκ
    -0.06
    AK
    -0.06
    .K
    -0.06
    Ar
    -0.06
    exion
    -0.06
     kond
    -0.06
    _BY
    -0.05
    írk
    -0.05
    POSITIVE LOGITS
     transferred
    0.08
     mw
    0.07
     договору
    0.07
     "#{
    0.07
     transferring
    0.07
     tw
    0.07
     nắng
    0.07
     trajectories
    0.06
     hides
    0.06
     �
    0.06
    Act Density 0.019%

    No Known Activations