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

    Neuronpedia

    INDEX
    Explanations

    relativity

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the stem “relativ-” (e.g. relativismo/relativize), i.e. words related to relativism.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ACT
    -0.07
     });↵↵
    -0.07
     forCellReuseIdentifier
    -0.06
    	expected
    -0.06
    듯
    -0.06
     skirts
    -0.06
    职
    -0.06
    이자
    -0.06
    .lista
    -0.06
     Mã
    -0.06
    POSITIVE LOGITS
     relativ
    0.09
    ",-
    0.07
    feedback
    0.07
     상대
    0.06
    (relative
    0.06
     obsc
    0.06
    centre
    0.06
     resolving
    0.06
     planet
    0.06
    hei
    0.06
    Act Density 0.005%

    No Known Activations