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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “moth,” especially in phrases stating that something is a moth in a taxonomic description.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Valent
    -0.06
    onaut
    -0.06
    岳
    -0.06
     nurt
    -0.06
    �
    -0.06
     Matters
    -0.06
    .handlers
    -0.06
    simd
    -0.06
    όδ
    -0.06
     Пет
    -0.06
    POSITIVE LOGITS
    =password
    0.06
    terdam
    0.06
    excerpt
    0.06
     травня
    0.06
    >');
    0.06
    (Student
    0.06
    >({↵
    0.06
    Vertical
    0.06
    abstract
    0.06
    unlock
    0.06
    Act Density 0.001%

    No Known Activations