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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_max-act · gemini-2.0-flash

    phrases related to legal issues or criminal activity.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on age expressions in the text (e.g. “2½-year-old,” “5½-month-old,” “14-month-old,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .pop
    -0.06
    						
↵
    -0.06
     더
    -0.06
    Histogram
    -0.06
     tricky
    -0.06
     tutoring
    -0.06
    .Clear
    -0.06
     ภาพ
    -0.05
     EXT
    -0.05
     Со
    -0.05
    POSITIVE LOGITS
     annual
    0.08
     ασ
    0.07
    uder
    0.07
     years
    0.07
    /npm
    0.07
     YEARS
    0.07
    نجليزية
    0.07
    Ѕ
    0.06
     Rehabilitation
    0.06
    ighter
    0.06
    Act Density 0.010%

    No Known Activations