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

    Neuronpedia

    INDEX
    Explanations

    [(

    np_max-act · gemini-2.0-flash

    The neuron activates on the opening square‐bracket and number sequence that begins the bracketed numbering in a chemical compound’s systematic name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    nob
    -0.07
    ิสต
    -0.07
    ์บ
    -0.07
    (sys
    -0.06
     obe
    -0.06
    Eng
    -0.06
     myself
    -0.06
    Disable
    -0.06
     Επ
    -0.06
    izing
    -0.06
    POSITIVE LOGITS
     [(
    0.10
    aghan
    0.08
     [
    0.07
    [(
    0.07
     astonished
    0.07
     Bruno
    0.07
     startDate
    0.07
    Ken
    0.06
     prz
    0.06
     Finch
    0.06
    Act Density 0.003%

    No Known Activations