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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “light” (and closely associated technical terms) in optical/imaging context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    elda
    -0.06
     سبک
    -0.06
     Wolves
    -0.06
    ۱۷
    -0.05
    -analytics
    -0.05
    arsity
    -0.05
     Ty
    -0.05
    .todo
    -0.05
    scape
    -0.05
    uckland
    -0.05
    POSITIVE LOGITS
     sexy
    0.07
    ючи
    0.07
    makta
    0.07
    -content
    0.07
     деятельности
    0.07
     JsonResult
    0.07
     Examination
    0.07
     DIM
    0.07
    `)↵
    0.06
    EFF
    0.06
    Act Density 0.017%

    No Known Activations