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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “together,” especially in phrases like “living together” describing cohabiting households.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dog
    -0.07
     pods
    -0.07
     serpent
    -0.07
     Eg
    -0.06
     worn
    -0.06
    or
    -0.06
     equivalents
    -0.06
    Inv
    -0.06
     eos
    -0.06
     Woods
    -0.06
    POSITIVE LOGITS
     رنگ
    0.07
     ресурс
    0.07
     확실
    0.06
    getToken
    0.06
     пищ
    0.06
     financially
    0.06
    pendicular
    0.06
    adata
    0.06
    완료
    0.06
    ساس
    0.06
    Act Density 0.001%

    No Known Activations