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

    Neuronpedia

    INDEX
    Explanations

    local

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “locally,” i.e. when a text refers to something being “locally” some property.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fist
    -0.09
    姫
    -0.07
     song
    -0.07
     Aure
    -0.07
    _hierarchy
    -0.07
    _dir
    -0.06
    ители
    -0.06
    trail
    -0.06
    _paid
    -0.06
    02
    -0.06
    POSITIVE LOGITS
     rehab
    0.06
     infinit
    0.06
    ]=="
    0.06
    �
    0.06
     MCP
    0.06
    (Cell
    0.06
     GC
    0.06
    (events
    0.06
     oyuncu
    0.06
    โรงเร
    0.06
    Act Density 0.004%

    No Known Activations