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

    Neuronpedia

    INDEX
    Explanations

    Ordinal suffixes

    np_max-act · gemini-2.0-flash

    The neuron detects ordinal numeric expressions (e.g. “7th,” “10th,” “58th,” “31st”) used as part of unit or corps designations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _rel
    -0.07
     Initializes
    -0.07
     trous
    -0.06
     valeur
    -0.06
     uncompressed
    -0.06
    <Menu
    -0.06
     similarity
    -0.06
    附
    -0.06
    료
    -0.06
    iterals
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    hashCode
    0.06
    sPid
    0.06
    RoutingModule
    0.06
     Лу
    0.06
    いて
    0.06
    ]->
    0.06
    abs
    0.06
     ~/.
    0.06
     Gast
    0.06
    Act Density 0.009%

    No Known Activations