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

    Neuronpedia

    INDEX
    Explanations

    relationships between variables

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the term “event” (especially in the phrase “other event”) in the instructions defining causal narratives.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     launch
    -0.07
     compl
    -0.06
     extensive
    -0.06
    ลำ
    -0.06
     Hide
    -0.06
     �
    -0.06
    recur
    -0.06
     simulated
    -0.06
    옥
    -0.06
    ман
    -0.06
    POSITIVE LOGITS
     Sections
    0.07
    uthor
    0.07
    年の
    0.06
     Specialist
    0.06
    Tips
    0.06
     ทาง
    0.06
     naturally
    0.06
     Scalars
    0.06
    .dimension
    0.06
     DisplayName
    0.06
    Act Density 0.001%

    No Known Activations