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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron is picking up on C++ namespace declarations (the “namespace” keyword and its associated tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     його
    -0.06
     永
    -0.06
     Αγγ
    -0.06
    子供
    -0.06
     haul
    -0.06
    must
    -0.06
    用
    -0.06
    171
    -0.06
    811
    -0.06
    arrival
    -0.06
    POSITIVE LOGITS
     glVertex
    0.07
     gardens
    0.07
     gql
    0.06
     GAP
    0.06
    غال
    0.06
    .feature
    0.06
     mutate
    0.06
     extravag
    0.06
    ुआ
    0.06
    aper
    0.06
    Act Density 0.003%

    No Known Activations