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

    Neuronpedia

    INDEX
    Explanations

    chemical structures and bonds

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numerical values (especially decimals) and their associated units in the description of crystallographic and structural measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lien
    -0.07
     polite
    -0.07
     project
    -0.06
    cepts
    -0.06
    >List
    -0.06
    Flo
    -0.06
     Danh
    -0.06
     coworkers
    -0.06
     shirt
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    restricted
    0.06
    leşme
    0.06
    ialog
    0.06
     specialize
    0.06
     обычно
    0.06
    ęp
    0.06
     surveyed
    0.06
    ACITY
    0.06
     Tanrı
    0.06
    educated
    0.06
    Act Density 0.007%

    No Known Activations