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

    Neuronpedia

    INDEX
    Explanations

    Period (sentence end)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tedious
    -0.07
     unnecessarily
    -0.07
     spec
    -0.07
    撥
    -0.07
    끄
    -0.07
    หมวด
    -0.07
     самого
    -0.06
    墅
    -0.06
    ไหล
    -0.06
    같
    -0.06
    POSITIVE LOGITS
     lowest
    0.08
     Lowest
    0.07
     modifications
    0.07
    resar
    0.07
    _fr
    0.07
     Fisheries
    0.07
     María
    0.06
    #,
    0.06
     altered
    0.06
     celular
    0.06
    Act Density 0.132%

    No Known Activations